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. 8588
    Prev
    Next
    INDEX
    Explanations

    prefixes for topics

    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
     for
    -0.85
    settle
    -0.78
     by
    -0.76
     while
    -0.76
     from
    -0.75
     an
    -0.74
     at
    -0.73
     getBy
    -0.72
     will
    -0.72
     when
    -0.72
    POSITIVE LOGITS
    Optional
    0.91
    ACTED
    0.89
    Profile
    0.86
    报表
    0.86
    OPTIONAL
    0.84
    optional
    0.83
    ICT
    0.83
    Know
    0.81
    Props
    0.80
    oração
    0.79
    Activations Density 0.019%

    No Known Activations