© 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. 70092
    Prev
    Next
    INDEX
    Explanations

    bypass graft

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

    commas (punctuation) in code and documentation contexts.

    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
    tetrahydro
    -0.77
    Nombres
    -0.69
    LOY
    -0.69
     XXXX
    -0.69
     Dundas
    -0.68
     炭
    -0.67
     מג
    -0.66
    vcs
    -0.65
    XW
    -0.65
    tech
    -0.65
    POSITIVE LOGITS
    TextAppearance
    0.73
     Swa
    0.69
    Masked
    0.67
    торой
    0.66
     fondo
    0.64
    탕
    0.64
    Bree
    0.64
    ildi
    0.63
     []).
    0.63
    Applause
    0.63
    Activations Density 0.063%

    No Known Activations