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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109657
    Prev
    Next
    INDEX
    Explanations

    vehicle assistance

    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
    הערות
    -0.75
    insegna
    -0.68
     welches
    -0.68
    珉
    -0.68
    fantasia
    -0.68
    ahal
    -0.66
    meetings
    -0.66
     Vert
    -0.66
    ikkert
    -0.65
     blk
    -0.65
    POSITIVE LOGITS
    estimate
    0.65
     taping
    0.63
    icao
    0.62
     ER
    0.62
    ান
    0.60
     Parity
    0.60
     tap
    0.59
     consult
    0.59
    ANES
    0.59
    トロ
    0.59
    Activations Density 0.060%

    No Known Activations