© 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. 93362
    Prev
    Next
    INDEX
    Explanations

    chromosome regions or locations

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

    genetic chromosome locations represented by numbers followed by 'p' or 'q'.

    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
    two
    -0.84
    往上
    -0.77
    four
    -0.77
    three
    -0.76
    ➅
    -0.76
     
    -0.75
    five
    -0.75
    seven
    -0.75
    apse
    -0.74
    ium
    -0.72
    POSITIVE LOGITS
     bagged
    0.77
     Andrés
    0.74
     XX
    0.71
    perturb
    0.71
    ıla
    0.71
    拳
    0.71
    ディー
    0.70
    失望
    0.70
    &:
    0.69
    zny
    0.69
    Activations Density 0.225%

    No Known Activations