© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 63918
    Prev
    Next
    INDEX
    Explanations

    programming types with generics

    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_34/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
     (
    -0.97
     and
    -0.94
    concepts
    -0.82
    luste
    -0.81
     carol
    -0.80
    ="
    -0.79
    Souza
    -0.79
     or
    -0.77
     ESTADO
    -0.74
     (%
    -0.73
    POSITIVE LOGITS
     of
    1.69
    <
    1.04
     '-';
    0.93
    тисти
    0.90
    етесь
    0.89
     descri
    0.88
    ᒪ
    0.85
    มาะ
    0.84
     없습니다
    0.84
    差点
    0.83
    Activations Density 0.014%

    No Known Activations