© 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. 10-GEMMASCOPE-RES-131K
    7. 72876
    Prev
    Next
    INDEX
    Explanations

    scientific identifiers

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

    DNA/RNA nucleotide sequences and hexadecimal codes.

    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_10/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
    であった
    -1.91
     we
    -1.82
    How
    -1.77
    T
    -1.77
    enuta
    -1.73
    x
    -1.70
    PreExecute
    -1.66
    C
    -1.66
     количество
    -1.65
    A
    -1.65
    POSITIVE LOGITS
     膠
    1.92
    ㈰
    1.91
    熜
    1.84
    ㈯
    1.79
     放題
    1.77
    嫫
    1.74
    Meu
    1.66
    ↵
    1.65
     酥
    1.64
    给大家
    1.63
    Activations Density 0.010%

    No Known Activations