© 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. 63621
    Prev
    Next
    INDEX
    Explanations

    password or either

    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
     first
    -0.76
    |_
    -0.74
     件
    -0.73
    =_
    -0.71
     find
    -0.68
     Mid
    -0.68
    Mid
    -0.67
    [__
    -0.66
     confetti
    -0.66
    ∂
    -0.64
    POSITIVE LOGITS
     redacción
    0.82
     enactment
    0.76
     برش
    0.73
    oyang
    0.69
     Ohl
    0.69
     acondicion
    0.68
    introdu
    0.68
     визу
    0.68
    spu
    0.66
    gulation
    0.66
    Activations Density 0.071%

    No Known Activations