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. 71
    Prev
    Next
    INDEX
    Explanations

    have received / called when / Start method

    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
    MISC
    -0.99
     správ
    -0.94
     článek
    -0.86
     compatri
    -0.85
    ఈ
    -0.85
     obok
    -0.82
     $*
    -0.82
     alors
    -0.80
     Quais
    -0.80
     znajdziesz
    -0.80
    POSITIVE LOGITS
    について
    1.02
     before
    0.99
     called
    0.91
     after
    0.85
     pre
    0.82
    太好了
    0.81
     when
    0.81
    dahl
    0.81
    により
    0.80
     llamó
    0.80
    Activations Density 0.003%

    No Known Activations