© 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. 22-GEMMASCOPE-RES-131K
    7. 34171
    Prev
    Next
    INDEX
    Explanations

    queue data structures

    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
     гораздо
    -2.50
    咴
    -2.42
     другой
    -2.31
    这里
    -2.31
    
    -2.28
    T
    -2.27
    H
    -2.27
     такой
    -2.27
    饹
    -2.23
     Handlungen
    -2.16
    POSITIVE LOGITS
    '
    3.28
     of
    2.20
     Kø
    2.17
    bangun
    2.13
     vaisselle
    2.06
     secador
    2.06
     Vå
    2.05
     permitem
    2.02
     boisson
    1.99
     brinde
    1.98
    Activations Density 0.011%

    No Known Activations