© 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. 109711
    Prev
    Next
    INDEX
    Explanations

    for reasons

    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
     from
    -1.05
     for
    -0.99
    omenti
    -0.90
    了不少
    -0.89
     where
    -0.88
    ácidos
    -0.88
    butuhkan
    -0.86
     marcato
    -0.84
    følgelig
    -0.84
     hetzelfde
    -0.83
    POSITIVE LOGITS
     reasons
    1.65
     Reasons
    1.48
    reasons
    1.42
     related
    1.40
    Reasons
    1.38
     REASONS
    1.16
     unknown
    1.14
    Related
    1.13
     unrelated
    1.12
     razones
    1.12
    Activations Density 0.042%

    No Known Activations