© 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. 36032
    Prev
    Next
    INDEX
    Explanations

    code annotations

    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
     bisous
    -1.59
    lampe
    -1.59
     manualidades
    -1.58
     biela
    -1.56
    nowy
    -1.53
    Trichloroethane
    -1.52
    junge
    -1.49
     délicieux
    -1.48
    resave
    -1.46
    ſtra
    -1.45
    POSITIVE LOGITS
    It
    1.69
    u
    1.66
    is
    1.59
    </em>
    1.55
     You
    1.45
     If
    1.43
    N
    1.38
     This
    1.33
    T
    1.33
    ro
    1.32
    Activations Density 0.003%

    No Known Activations