© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77424
    Prev
    Next
    INDEX
    Explanations

    prevalence and characteristics

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

    indentation and whitespace in source code files, especially at the beginning of new lines.

    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
     squamous
    -0.75
     Licht
    -0.70
    რ
    -0.69
     unreasonably
    -0.68
     CLE
    -0.68
    証拠
    -0.68
    illie
    -0.67
    纱
    -0.67
    战术
    -0.67
    ɺ
    -0.65
    POSITIVE LOGITS
    nitz
    0.77
     PRESIDENT
    0.69
    系列
    0.69
    enium
    0.67
     कोई
    0.65
     NATIONS
    0.65
    aden
    0.64
    zke
    0.63
    dieux
    0.63
    zkę
    0.63
    Activations Density 0.057%

    No Known Activations