© 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. 22-GEMMASCOPE-RES-131K
    7. 71990
    Prev
    Next
    INDEX
    Explanations

    pot or words starting with pot

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    on
    -2.86
    be
    -2.73
    was
    -2.72
    or
    -2.64
    m
    -2.59
    C
    -2.52
    T
    -2.48
    ve
    -2.45
    il
    -2.44
    h
    -2.44
    POSITIVE LOGITS
    ᷆
    2.61
    鉏
    2.59
     tetapi
    2.50
    mazioni
    2.44
    viedo
    2.34
    쨩
    2.34
    tym
    2.31
    zembro
    2.31
    </strong>
    2.30
     kunnen
    2.30
    Activations Density 0.011%

    No Known Activations