© 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. 48763
    Prev
    Next
    INDEX
    Explanations

    anesthetics | structural | common

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

    file path or package structure elements in programming code.

    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
     összefoglal
    -0.92
     összefoglaló
    -0.81
    Jaunes
    -0.77
     aanbied
    -0.76
    吾
    -0.75
    tando
    -0.75
     зим
    -0.73
    /*",
    -0.73
    ẁ
    -0.73
    錮
    -0.71
    POSITIVE LOGITS
     common
    0.92
    ecore
    0.89
    common
    0.85
    還有
    0.82
     còn
    0.82
    äksi
    0.81
    Structural
    0.81
     structural
    0.81
    zá
    0.78
    loha
    0.77
    Activations Density 0.004%

    No Known Activations