© 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. 95846
    Prev
    Next
    INDEX
    Explanations

    how things can be done

    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
     tromper
    -1.16
    ܇
    -1.13
     réfrig
    -1.11
     arbre
    -1.10
     peintures
    -1.09
     délais
    -1.09
     bolsillos
    -1.09
    뻣
    -1.09
     cordes
    -1.09
    performs
    -1.07
    POSITIVE LOGITS
     using
    1.67
     with
    1.58
     can
    1.46
     requires
    1.29
     require
    1.29
     into
    1.27
     successfully
    1.27
     requiring
    1.27
     by
    1.27
     easily
    1.22
    Activations Density 0.188%

    No Known Activations