© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58688
    Prev
    Next
    INDEX
    Explanations

    life, living organisms, creatures

    np_acts-logits-general · gemini-2.5-flash-lite

    phrases that describe biological relationships where one organism or entity depends on or affects others in an ecosystem.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron is triggered by universal‐scope quantifier phrases—words like “all,” “nearly all,” or “almost all” that assert something applies to the entire group.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Synth
    -0.81
    Feet
    -0.71
     Feet
    -0.70
     Torr
    -0.70
    uz
    -0.70
    feet
    -0.70
    şe
    -0.68
     keyboard
    -0.68
     camas
    -0.68
     tomb
    -0.68
    POSITIVE LOGITS
     living
    4.78
    living
    3.50
    Living
    3.34
     Living
    3.30
     LIVING
    2.92
    LIVING
    2.69
     жи
    2.50
     creatures
    2.31
     organisms
    2.31
     animate
    2.27
    Activations Density 0.136%

    No Known Activations