© 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. 65579
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

    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
     rosario
    -1.54
    jusqu
    -1.44
     деца
    -1.30
     csapat
    -1.28
    lamabad
    -1.27
     舞台
    -1.27
     emporio
    -1.27
     pascua
    -1.27
     детей
    -1.25
     geene
    -1.23
    POSITIVE LOGITS
     if
    1.82
     to
    1.49
     as
    1.28
     ,
    1.27
     Since
    1.23
     and
    1.19
     p
    1.17
     more
    1.15
     -
    1.14
    ,
    1.14
    Activations Density 0.132%

    No Known Activations