© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 73430
    Prev
    Next
    INDEX
    Explanations

    gene cloning

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

    random character sequences or tokens in URLs and code identifiers.

    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
     ketentuan
    -0.81
    GenerationType
    -0.80
     グラン
    -0.77
     made
    -0.77
    makedirs
    -0.75
    ரை
    -0.73
     nitrous
    -0.72
    准
    -0.71
     outs
    -0.70
    abler
    -0.70
    POSITIVE LOGITS
    uw
    0.85
    GQ
    0.84
     TQ
    0.84
    jg
    0.84
    yg
    0.82
     GQ
    0.80
    vw
    0.80
    lg
    0.80
    qw
    0.80
    cg
    0.79
    Activations Density 0.031%

    No Known Activations