© 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. 39135
    Prev
    Next
    INDEX
    Explanations

    that's how

    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
     and
    -1.50
    ַּ
    -1.47
     vocale
    -1.46
     constater
    -1.38
     camicia
    -1.36
    ctional
    -1.36
    FFECT
    -1.34
    ásticas
    -1.34
     dovre
    -1.33
     felice
    -1.33
    POSITIVE LOGITS
     what
    3.05
     how
    2.95
     where
    2.63
     why
    2.58
     when
    1.89
     the
    1.61
     who
    1.52
    /
    1.48
    '
    1.46
     whom
    1.39
    Activations Density 0.019%

    No Known Activations