© 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. 42295
    Prev
    Next
    INDEX
    Explanations

    phot, itertools, IOS

    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
    ’
    -3.25
    珢
    -3.02
    "
    -2.63
    ８
    -2.52
    It
    -2.52
     they
    -2.44
    at
    -2.42
    $
    -2.42
    you
    -2.38
    涐
    -2.38
    POSITIVE LOGITS
     are
    2.88
    chnung
    2.75
     reiterate
    2.70
     surpass
    2.69
     кухо
    2.66
     fulfill
    2.64
     ที่
    2.56
     ו
    2.53
     fulfil
    2.53
     और
    2.47
    Activations Density 0.026%

    No Known Activations