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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 69
    Prev
    Next
    INDEX
    Explanations

    internal development and production

    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
    ffc
    -0.79
     suivantes
    -0.77
    PreInfinity
    -0.75
    individ
    -0.75
     suivants
    -0.74
    راب
    -0.73
    optionalTypeArgs
    -0.73
    GetAsync
    -0.73
    rawa
    -0.72
    ofia
    -0.71
    POSITIVE LOGITS
     internal
    5.63
    internal
    4.81
     internally
    4.44
    Internal
    3.94
    内部
    3.88
    INTERNAL
    3.80
     Internal
    3.73
     INTERNAL
    3.48
     interno
    3.47
     wewnętr
    3.39
    Activations Density 0.082%

    No Known Activations