© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108606
    Prev
    Next
    INDEX
    Explanations

    free software and framework

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     Prov
    -0.69
    自家
    -0.69
    vati
    -0.64
    ischen
    -0.64
     prov
    -0.63
     Libro
    -0.62
     berkata
    -0.60
    ၎
    -0.60
     wiederhol
    -0.60
     जाएगा
    -0.60
    POSITIVE LOGITS
    沪
    0.71
    paramref
    0.71
     Xa
    0.70
    pNext
    0.69
    Char
    0.69
    Addo
    0.69
    Sar
    0.68
    jaman
    0.67
    medies
    0.66
    ldo
    0.66
    Activations Density 0.111%

    No Known Activations