© 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. 10-GEMMASCOPE-RES-131K
    7. 102892
    Prev
    Next
    INDEX
    Explanations

    chitosan, bricks, polycarbonate

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

    The neuron detects the word "chitosan" and related chemical/polymer terminology.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     giy
    -2.28
    粜
    -2.27
    퐼
    -2.25
     lagerfeld
    -2.19
     niedersachsen
    -2.16
    »:
    -2.14
     ongles
    -2.11
     iyo
    -2.09
    ーズン
    -2.08
    ꪔ
    -2.08
    POSITIVE LOGITS
     So
    2.50
     It
    2.48
     Not
    2.22
     When
    2.19
    er
    2.11
     At
    2.08
     '
    1.97
    でもいい
    1.95
     Does
    1.95
     You
    1.95
    Activations Density 0.005%

    No Known Activations