© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 16088
    Prev
    Next
    INDEX
    Explanations

    common sentence starters

    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
    を
    -2.17
    が
    -2.05
    そして
    -1.85
    と
    -1.70
    は
    -1.63
    では
    -1.59
    6
    -1.58
    で
    -1.56
    4
    -1.55
     الخاص
    -1.53
    POSITIVE LOGITS
     There
    1.88
    為に
    1.87
     So
    1.76
     What
    1.69
     They
    1.66
     Some
    1.63
     That
    1.56
     Here
    1.55
     For
    1.55
     It
    1.52
    Activations Density 0.064%

    No Known Activations