© 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. 10-GEMMASCOPE-RES-131K
    7. 7061
    Prev
    Next
    INDEX
    Explanations

    face to face

    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_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
    {
    -3.08
    >
    -2.38
    ”,
    -2.06
     you
    -1.88
    ></
    -1.66
    )։
    -1.66
    導致
    -1.63
     após
    -1.63
     asociado
    -1.63
    ),
    -1.62
    POSITIVE LOGITS
    沨
    2.13
    zeniu
    1.97
     raiſ
    1.96
    夘
    1.91
    ⑊
    1.91
    蕖
    1.83
     ,"
    1.83
     firsthand
    1.79
    〣
    1.78
    THEN
    1.77
    Activations Density 0.004%

    No Known Activations