© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12462
    Prev
    Next
    INDEX
    Explanations

    the word hint

    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
     réalisées
    -2.36
     pero
    -2.25
     одном
    -2.19
     nhưng
    -2.19
    żli
    -2.16
    -2.16
    臯
    -2.09
    ارتمان
    -2.06
     unmöglich
    -2.02
     o
    -2.00
    POSITIVE LOGITS
     řekl
    2.44
    此事
    2.36
     fueran
    2.33
     quedará
    2.25
    蜮
    2.23
     praktis
    2.22
     IBRARY
    2.22
    駡
    2.13
    .
    2.11
     pérd
    2.09
    Activations Density 0.009%

    No Known Activations