© 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. 77868
    Prev
    Next
    INDEX
    Explanations

    code snippets and programming constructs

    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
    Highway
    -0.71
     Highways
    -0.69
     highways
    -0.69
    尖叫
    -0.68
     Lover
    -0.65
    HIGH
    -0.65
    Sample
    -0.64
    種の
    -0.64
    Segments
    -0.63
     oregon
    -0.63
    POSITIVE LOGITS
    ']").
    0.74
    hran
    0.71
     مشين
    0.68
    ཧ
    0.66
     Recreational
    0.66
    ایید
    0.66
    addCell
    0.65
    \%)
    0.65
    mento
    0.65
    PageState
    0.65
    Activations Density 0.027%

    No Known Activations