© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35081
    Prev
    Next
    INDEX
    Explanations

    digits and punctuation combined

    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
     its
    -1.23
     japones
    -1.20
     tableta
    -1.16
     it
    -1.16
    dekat
    -1.11
    ėjimas
    -1.04
     escote
    -0.99
    plom
    -0.98
    lihatan
    -0.96
     or
    -0.96
    POSITIVE LOGITS
    haped
    1.13
    tened
    1.05
    ns
    1.03
     derselben
    1.00
    heet
    1.00
    orship
    1.00
    atization
    1.00
    osaurus
    1.00
    ans
    0.99
    alisation
    0.98
    Activations Density 0.003%

    No Known Activations