© 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. 22-GEMMASCOPE-RES-131K
    7. 38479
    Prev
    Next
    INDEX
    Explanations

    making sure of outcomes

    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_22/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
     PUSTAKA
    -2.53
    🪆
    -2.20
     целей
    -2.14
    떳
    -2.14
    雱
    -2.09
    戆
    -2.06
    姈
    -2.05
    section
    -2.05
    ⬈
    -2.00
     использовании
    -1.95
    POSITIVE LOGITS
     that
    3.47
    綃
    2.39
    ور
    2.30
    j
    2.03
    (
    2.03
    喼
    1.97
     kela
    1.93
     Dieses
    1.91
     Ähnliche
    1.89
     Siehe
    1.87
    Activations Density 0.007%

    No Known Activations