© 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. 34-GEMMASCOPE-RES-131K
    7. 48452
    Prev
    Next
    INDEX
    Explanations

    compounds found in or released from

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

    chemical compounds and scientific substances in biological or scientific texts.

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

    The neuron flags mentions of chemical compounds or scientific substance names.

    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
     for
    -1.04
     by
    -1.02
     was
    -1.00
     where
    -0.99
    ultad
    -0.95
     four
    -0.95
    weightedMode
    -0.94
     took
    -0.92
     with
    -0.90
    所示
    -0.88
    POSITIVE LOGITS
     found
    1.84
     present
    1.78
    contained
    1.64
    found
    1.52
     contained
    1.38
     responsible
    1.33
     contenu
    1.33
    Found
    1.28
     released
    1.22
    present
    1.22
    Activations Density 0.215%

    No Known Activations