© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 84058
    Prev
    Next
    INDEX
    Explanations

    c preprocessor includes

    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
     when
    -0.85
    beige
    -0.82
     ketika
    -0.80
     pertandingan
    -0.79
     Jér
    -0.78
    municipi
    -0.78
    ANDRA
    -0.77
    pox
    -0.77
    ~=
    -0.76
    óngase
    -0.76
    POSITIVE LOGITS
    int
    0.95
     cóc
    0.82
     フィ
    0.78
     REGULAR
    0.73
    бо
    0.72
     claridad
    0.71
    ulso
    0.71
    indent
    0.70
    getStyle
    0.70
     stalwart
    0.69
    Activations Density 0.004%

    No Known Activations