© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 118652
    Prev
    Next
    INDEX
    Explanations

    expression, titanium, Norway, Benin

    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
    vão
    -0.78
     Οι
    -0.73
    Smash
    -0.73
     グ
    -0.72
    OMAN
    -0.72
     luon
    -0.71
     ominous
    -0.71
    ровна
    -0.71
     Mí
    -0.69
    від
    -0.69
    POSITIVE LOGITS
     Dayton
    0.96
     Cincinnati
    0.96
     prefixed
    0.88
    Ohio
    0.86
     hl
    0.81
     IX
    0.81
    шил
    0.81
     Ohio
    0.81
    Cincinnati
    0.78
     USSR
    0.77
    Activations Density 0.009%

    No Known Activations