© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 36137
    Prev
    Next
    INDEX
    Explanations

    academic document citations

    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
    empereur
    -1.01
     anbef
    -0.97
     måtte
    -0.89
     spesielt
    -0.88
    گزاری
    -0.85
     chiunque
    -0.84
     raccomand
    -0.83
     econômica
    -0.82
     demands
    -0.81
    もなく
    -0.81
    POSITIVE LOGITS
    cracy
    1.01
     invités
    0.95
     spectrophoto
    0.92
    うえ
    0.91
     and
    0.89
    eably
    0.86
    nées
    0.86
    REEN
    0.84
    bobox
    0.84
    agos
    0.83
    Activations Density 0.005%

    No Known Activations