© 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. 10-GEMMASCOPE-RES-131K
    7. 69681
    Prev
    Next
    INDEX
    Explanations

    phrases starting with #

    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
     ſont
    -1.66
     cresce
    -1.60
     MULTIPLE
    -1.49
     gấu
    -1.49
    Cevap
    -1.46
     ludicrous
    -1.44
    Bisous
    -1.44
    姤
    -1.43
     soooo
    -1.42
     luscious
    -1.40
    POSITIVE LOGITS
     for
    2.42
    If
    2.31
    It
    2.17
    When
    2.16
    After
    2.03
    These
    1.93
    For
    1.85
    　※
    1.85
    This
    1.75
    There
    1.73
    Activations Density 0.072%

    No Known Activations