© 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. 78095
    Prev
    Next
    INDEX
    Explanations

    code, comments, and specifications

    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
    Ң
    -0.88
     vody
    -0.84
    bürgermeister
    -0.79
     nedan
    -0.79
     sambung
    -0.79
     consommateurs
    -0.78
    ligo
    -0.77
     Restra
    -0.76
    凉
    -0.76
     Unsupported
    -0.76
    POSITIVE LOGITS
     notification
    0.82
     이해
    0.80
    ジナル
    0.79
    éges
    0.76
    审核
    0.73
     通知
    0.72
    ому
    0.71
     mejores
    0.71
     die
    0.70
    通知
    0.70
    Activations Density 0.000%

    No Known Activations