© 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. 117394
    Prev
    Next
    INDEX
    Explanations

    package dependency resolution

    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
     残
    -0.76
    伀
    -0.73
     задний
    -0.68
    icked
    -0.68
    tein
    -0.68
    Byte
    -0.66
     vernis
    -0.66
    Nich
    -0.66
     terug
    -0.65
     rencontr
    -0.65
    POSITIVE LOGITS
    lás
    0.69
    GRU
    0.68
    SideBar
    0.66
    llas
    0.66
     enemmän
    0.65
     vecchia
    0.64
     getSub
    0.63
     hydropower
    0.62
    되었습니다
    0.61
    уда
    0.60
    Activations Density 0.061%

    No Known Activations