© 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. 130093
    Prev
    Next
    INDEX
    Explanations

    mold and its contexts

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

    The neuron primarily detects the word "mold" and its variations (such as "molding"), with particularly high activation for the standalone noun form.

    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
    vantaged
    -2.94
     That
    -2.67
     que
    -2.41
     Not
    -2.36
     downsides
    -2.25
    ჻
    -2.25
     $\
    -2.16
    甚
    -2.13
     lograr
    -2.11
    עו
    -2.09
    POSITIVE LOGITS
    ꒥
    2.94
    釭
    2.52
     rivista
    2.44
    蠖
    2.38
    {
    2.36
    ᐡ
    2.36
     одежды
    2.33
    la
    2.33
    㩒
    2.33
    </strong>
    2.30
    Activations Density 0.006%

    No Known Activations