© 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. 3081
    Prev
    Next
    INDEX
    Explanations

    attorneys

    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
    strlen
    -0.82
    Actions
    -0.77
    removeClass
    -0.76
     dilute
    -0.76
    lify
    -0.75
    olutamente
    -0.74
     Motions
    -0.74
     Actions
    -0.73
    tellt
    -0.73
     Chua
    -0.73
    POSITIVE LOGITS
    出品
    0.75
    还可以
    0.70
    Identific
    0.70
    予報
    0.70
    山中
    0.69
    قامة
    0.68
     indexOf
    0.66
     şun
    0.65
    主人
    0.63
    posx
    0.62
    Activations Density 0.054%

    No Known Activations