© 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. 10-GEMMASCOPE-RES-131K
    7. 22456
    Prev
    Next
    INDEX
    Explanations

    attention-grabbing headers and warnings

    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_10/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
     каждый
    -1.52
    潯
    -1.49
     Брази
    -1.48
     każdego
    -1.48
    の場合
    -1.43
     każdym
    -1.40
     своих
    -1.38
     poszczegól
    -1.38
     когато
    -1.35
    🫴
    -1.33
    POSITIVE LOGITS
    .
    1.99
     a
    1.75
     Currently
    1.70
    咚
    1.53
     menyukai
    1.51
    Currently
    1.50
    輊
    1.45
     an
    1.45
     tertarik
    1.45
     Although
    1.42
    Activations Density 0.033%

    No Known Activations