© 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. 22-GEMMASCOPE-RES-131K
    7. 15239
    Prev
    Next
    INDEX
    Explanations

    genetic diversity

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

    vertical whitespace and formatting in text, particularly navigation sections or headers.

    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_22/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
    Responder
    -0.98
     وكذلك
    -0.91
    アサ
    -0.89
    vasive
    -0.84
     şirket
    -0.83
     Shearer
    -0.83
     食物
    -0.83
     ошибок
    -0.82
    Responsibilities
    -0.81
    formatics
    -0.81
    POSITIVE LOGITS
     abandonar
    1.01
    ˜
    0.95
     with
    0.89
    比べて
    0.88
    erecht
    0.88
     new
    0.87
     lead
    0.86
    来店
    0.85
     psicológica
    0.83
     using
    0.82
    Activations Density 0.000%

    No Known Activations