© 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. 39020
    Prev
    Next
    INDEX
    Explanations

    lists and concepts

    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
    ですので
    -1.23
    前は
    -1.20
    などなど
    -1.12
    ݨ
    -1.11
    そして
    -1.08
    声が
    -1.07
    かで
    -1.06
    があります
    -1.06
    での
    -1.05
    よろしくお願い
    -1.05
    POSITIVE LOGITS
    ことも
    1.23
     नहीं
    1.20
     nessuno
    1.15
    のではない
    1.14
    Décès
    1.13
    ためには
    1.13
    のではないか
    1.11
     gratuits
    1.10
    सि
    1.10
     falda
    1.10
    Activations Density 0.265%

    No Known Activations