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. 8299
    Prev
    Next
    INDEX
    Explanations

    code language and comments

    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
     люби
    -0.84
    buya
    -0.75
    ᚖ
    -0.72
    xba
    -0.70
     docking
    -0.70
    ught
    -0.68
    老
    -0.67
    edific
    -0.66
    READ
    -0.66
    margin
    -0.66
    POSITIVE LOGITS
     dotato
    0.78
    kadın
    0.73
    reco
    0.72
    Preview
    0.69
     pageNo
    0.69
    🎧
    0.69
     игрушка
    0.68
     Pall
    0.68
    слі
    0.68
     CRACK
    0.68
    Activations Density 0.035%

    No Known Activations