© 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. 34-GEMMASCOPE-RES-131K
    7. 78254
    Prev
    Next
    INDEX
    Explanations

    superintendent, supernatant

    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
    ListResponse
    -0.90
    ேர
    -0.86
    SECON
    -0.84
    skor
    -0.84
     presupuesto
    -0.82
    fällen
    -0.81
     Vorstand
    -0.81
     cukup
    -0.81
    諼
    -0.77
    에는
    -0.77
    POSITIVE LOGITS
    Super
    1.20
     SUPER
    1.05
     Super
    1.00
    ال
    0.98
    Ці
    0.97
     super
    0.96
    Это
    0.94
     súper
    0.94
    uper
    0.93
     スーパー
    0.93
    Activations Density 0.036%

    No Known Activations