© 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. 99331
    Prev
    Next
    INDEX
    Explanations

    May dates

    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
    .”
    -2.92
     với
    -2.11
    ,’
    -2.03
    ,“
    -2.03
     caseros
    -2.02
     are
    -2.02
    
    -2.00
     finds
    -1.99
    ’
    -1.98
    媖
    -1.98
    POSITIVE LOGITS
    <td>
    2.05
    ⩥
    1.99
    ܆
    1.84
    {
    1.77
     Its
    1.77
    糁
    1.76
    were
    1.66
    鴴
    1.62
    S
    1.59
    during
    1.59
    Activations Density 0.044%

    No Known Activations