Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8552
    Prev
    Next
    INDEX
    Explanations

    birth information

    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
     actionTypes
    -1.05
    amental
    -1.02
    气质
    -0.97
     CONTRIBUTION
    -0.96
     Otras
    -0.94
    anmar
    -0.93
     WHEREAS
    -0.90
     Cualquier
    -0.89
    vana
    -0.88
    malige
    -0.88
    POSITIVE LOGITS
     Born
    1.46
     born
    1.26
    Born
    1.16
     son
    1.12
     formerly
    1.04
     Mr
    1.02
     filho
    1.01
     daughter
    0.99
     survivors
    0.97
     widow
    0.95
    Activations Density 0.014%

    No Known Activations