© 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. 79807
    Prev
    Next
    INDEX
    Explanations

    scientific names or code punctuation

    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
     to
    -1.35
     on
    -1.18
     that
    -1.01
    en
    -0.98
     of
    -0.97
     chosen
    -0.96
     F
    -0.96
    眼前的
    -0.94
     are
    -0.93
     No
    -0.93
    POSITIVE LOGITS
    modellen
    1.09
    Tudo
    1.06
    verlauf
    1.05
     allerlei
    1.04
     balení
    1.03
    Hilsen
    1.02
    Украина
    1.01
    verkauf
    1.01
    Kreuz
    0.96
    Frauen
    0.96
    Activations Density 0.009%

    No Known Activations