© 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. 93200
    Prev
    Next
    INDEX
    Explanations

    code identifiers and technical terms

    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
     of
    -1.55
     vorigen
    -1.15
     feuer
    -1.09
    ,
    -1.09
    ğın
    -1.04
    asking
    -1.02
    masque
    -1.01
    ঔ
    -0.98
     pasirink
    -0.97
     Heilige
    -0.95
    POSITIVE LOGITS
    ária
    1.26
     Pré
    1.25
    If
    1.25
    诸多
    1.19
     série
    1.18
    ᜀ
    1.18
    reté
    1.17
    ttää
    1.17
    titudes
    1.16
    ignée
    1.16
    Activations Density 0.067%

    No Known Activations