© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 15333
    Prev
    Next
    INDEX
    Explanations

    needs and availability of resources

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

    The neuron detects mentions of key resources or materials (e.g., pasture, organs, iron) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     of
    -1.21
    _
    -1.19
     it
    -1.19
    it
    -1.02
    گذاری
    -0.96
    k
    -0.96
    ub
    -0.93
     cowok
    -0.91
     Flasche
    -0.90
    acamole
    -0.90
    POSITIVE LOGITS
     for
    2.38
     to
    1.55
     needed
    1.45
     available
    1.38
     для
    1.32
     availability
    1.30
     from
    1.27
     supply
    1.18
     জন্য
    1.14
    available
    1.13
    Activations Density 0.075%

    No Known Activations