© 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. 65086
    Prev
    Next
    INDEX
    Explanations

    Japanese character writing

    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
    ategori
    -0.93
    licate
    -0.81
     alguns
    -0.77
    돗
    -0.76
     alun
    -0.76
    otus
    -0.74
     specialised
    -0.74
    these
    -0.74
     специаль
    -0.73
     Ähn
    -0.72
    POSITIVE LOGITS
     horizontal
    0.95
     there
    0.87
    cartItem
    0.82
    kope
    0.79
     FRIDAY
    0.78
    itaal
    0.77
     cómoda
    0.77
    wał
    0.75
     Horizontal
    0.75
    arkhand
    0.74
    Activations Density 0.011%

    No Known Activations