© 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. 26828
    Prev
    Next
    INDEX
    Explanations

    or conjunctions

    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
    several
    -1.39
     rè
    -1.33
    ֶּ
    -1.28
     perus
    -1.23
    一旁的
    -1.22
     ſever
    -1.22
    perfect
    -1.20
    ビックリ
    -1.20
     român
    -1.20
     ſol
    -1.20
    POSITIVE LOGITS
     as
    1.61
     or
    1.57
     like
    1.53
     from
    1.49
    或
    1.42
     not
    1.41
     مانند
    1.32
    That
    1.30
     because
    1.30
     That
    1.25
    Activations Density 0.029%

    No Known Activations