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. 8051
    Prev
    Next
    INDEX
    Explanations

    license aggregation

    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
     manger
    -0.77
    akte
    -0.77
    thof
    -0.73
     Rede
    -0.73
    JECTION
    -0.71
    sunt
    -0.71
     Gog
    -0.71
    akti
    -0.71
    тус
    -0.70
    SSID
    -0.70
    POSITIVE LOGITS
     even
    0.84
     Krieg
    0.75
     czo
    0.72
    竞
    0.68
     drastically
    0.66
    ka
    0.65
    يلات
    0.65
     expanding
    0.64
    흡
    0.63
     وليس
    0.63
    Activations Density 0.030%

    No Known Activations