© 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. 119037
    Prev
    Next
    INDEX
    Explanations

    guide/, decline at, Cross Fit, Oxaliplatin

    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
     what
    -0.87
     through
    -0.83
     probably
    -0.83
     less
    -0.82
     in
    -0.80
    porus
    -0.80
     focused
    -0.79
    НОВ
    -0.78
     because
    -0.77
     began
    -0.77
    POSITIVE LOGITS
     urat
    0.82
    Tempor
    0.80
     любы
    0.79
    whenever
    0.78
     bunt
    0.77
    camiento
    0.77
    かというと
    0.76
    easy
    0.76
    eight
    0.75
    belong
    0.75
    Activations Density 0.000%

    No Known Activations