© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 143288
    Prev
    Next
    INDEX
    Explanations

    foreign language words

    np_acts-logits-general · gemini-2.5-flash-lite

    discrete categorical data embeddings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Warsaw
    0.50
     maxHeight
    0.46
     plonge
    0.44
     기반
    0.43
     rebounds
    0.42
     é
    0.42
     wygląda
    0.42
     Luxor
    0.42
    &$
    0.42
    ่วง
    0.42
    POSITIVE LOGITS
     जेव्हा
    0.42
     Tabelle
    0.42
    یتے
    0.40
     diciendo
    0.40
    ٤
    0.39
    राने
    0.39
     jueves
    0.38
     Fehler
    0.38
    ندي
    0.38
     Variablen
    0.37
    Activations Density 0.001%

    No Known Activations