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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 10083
    Prev
    Next
    INDEX
    Explanations

    based on

    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_10/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
    на
    -2.97
    ’
    -2.86
    ."
    -2.27
    ка
    -2.25
     VERY
    -2.20
     totalement
    -2.20
    dersfield
    -2.19
    bten
    -2.14
     ABSOL
    -2.14
     ENTIRE
    -2.11
    POSITIVE LOGITS
     alleviate
    2.63
     those
    2.45
     using
    2.45
     that
    2.45
     having
    2.41
     utilize
    2.33
     incorporate
    2.33
     when
    2.31
     strengthen
    2.27
     enhance
    2.23
    Activations Density 0.032%

    No Known Activations