© 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. 33800
    Prev
    Next
    INDEX
    Explanations

    source file license

    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
     Noo
    -0.76
    电
    -0.74
    ietic
    -0.74
    立てる
    -0.72
    Metals
    -0.71
    явля
    -0.70
    पु
    -0.66
     poached
    -0.66
     mental
    -0.65
    metals
    -0.65
    POSITIVE LOGITS
     CALL
    0.75
    Hades
    0.73
    guest
    0.71
     bude
    0.67
    полага
    0.66
    Dati
    0.65
    ᕼ
    0.65
     Cooks
    0.65
     دانشگاه
    0.65
    iş
    0.65
    Activations Density 0.060%

    No Known Activations