© 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. 73697
    Prev
    Next
    INDEX
    Explanations

    ratios, indices, and quantitative metrics

    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
     зустрі
    -1.30
     verdaderas
    -1.25
     revoir
    -1.17
    struktur
    -1.16
    鴴
    -1.16
     supprimer
    -1.16
    тися
    -1.16
     насеко
    -1.12
    ),\
    -1.10
     fantasmas
    -1.10
    POSITIVE LOGITS
     of
    2.11
     for
    1.70
     (
    1.60
     on
    1.50
     between
    1.47
     by
    1.45
     as
    1.39
     which
    1.39
     also
    1.38
     in
    1.23
    Activations Density 0.090%

    No Known Activations