© 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. 34317
    Prev
    Next
    INDEX
    Explanations

    bib references with numbers

    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
    おわりに
    -1.55
     LIRE
    -1.45
     pérd
    -1.34
     icônes
    -1.29
     sesu
    -1.28
     vuitton
    -1.27
     péro
    -1.26
     guir
    -1.26
     multicolore
    -1.26
     fré
    -1.25
    POSITIVE LOGITS
     and
    2.02
     cierta
    1.16
     desses
    1.07
     numerosas
    1.05
     maravillas
    1.03
     Hochsch
    1.00
     Volkes
    0.99
     ~
    0.98
     rheinland
    0.97
     maravilh
    0.97
    Activations Density 0.001%

    No Known Activations