© 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. 71471
    Prev
    Next
    INDEX
    Explanations

    dates, numbers, states

    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
     from
    -1.45
     in
    -1.45
     to
    -1.44
     of
    -1.41
     for
    -1.41
     by
    -1.40
     on
    -1.34
    ;
    -1.34
     or
    -1.30
     However
    -1.27
    POSITIVE LOGITS
    klare
    1.59
    Bjs
    1.59
    Kontra
    1.54
    🩻
    1.51
    Gön
    1.49
     gewüns
    1.41
    ਗ਼
    1.40
    Kabel
    1.39
     tunik
    1.36
     hígado
    1.34
    Activations Density 0.002%

    No Known Activations