© 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. 98167
    Prev
    Next
    INDEX
    Explanations

    numbers and separators

    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
    cinhas
    -0.91
     dessus
    -0.85
    RTHOOK
    -0.78
     Apples
    -0.74
     lur
    -0.73
     نها
    -0.72
    気持ち
    -0.72
    ³,
    -0.70
     מי
    -0.69
    comfortably
    -0.69
    POSITIVE LOGITS
    țiunea
    0.77
    缁
    0.75
    يلي
    0.75
    manent
    0.74
    rican
    0.73
     raggiung
    0.71
    جوی
    0.71
    managers
    0.70
    OfBirth
    0.70
    rą
    0.70
    Activations Density 0.332%

    No Known Activations