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. 8162
    Prev
    Next
    INDEX
    Explanations

    ; followed by peptides

    np_acts-logits-general · gemini-2.5-flash-lite

    semicolons and symbols in technical or code-related content.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     mengerti
    -0.91
    dienne
    -0.89
     TextFormField
    -0.87
     whofe
    -0.87
     rigue
    -0.83
    👖
    -0.81
     nila
    -0.80
     paham
    -0.79
     vaqueros
    -0.79
     sexto
    -0.78
    POSITIVE LOGITS
     vilken
    0.96
     иной
    0.92
    tová
    0.84
    )}-\
    0.81
     infantry
    0.80
     öffnet
    0.80
     miesz
    0.78
     Angebot
    0.78
    ビタミン
    0.77
     BY
    0.77
    Activations Density 0.000%

    No Known Activations