© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117129
    Prev
    Next
    INDEX
    Explanations

    names or compounds

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

    last names in author attributions.

    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
    Another
    -0.88
     another
    -0.87
     mewujudkan
    -0.85
     Temmuz
    -0.78
     Another
    -0.73
    </h1>
    -0.73
    ganggu
    -0.72
    sions
    -0.72
     Rema
    -0.71
    Canceled
    -0.71
    POSITIVE LOGITS
    憶
    0.88
    vesen
    0.88
    AVY
    0.82
    슴
    0.80
    BIOGRAPHY
    0.80
     別注
    0.79
    INGREDIENTES
    0.79
    讫
    0.78
    経営
    0.78
     是否
    0.78
    Activations Density 0.088%

    No Known Activations