© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 68719
    Prev
    Next
    INDEX
    Explanations

    symbols and random strings

    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
    Negative Logits
    𖤣
    -1.62
     will
    -1.59
     quaint
    -1.58
     Each
    -1.53
     on
    -1.52
     to
    -1.48
     depender
    -1.45
    .?
    -1.44
     what
    -1.40
     Would
    -1.39
    POSITIVE LOGITS
     تحتوي
    1.73
    },
    1.66
    ctivité
    1.49
    which
    1.47
    ،
    1.45
     of
    1.41
    since
    1.41
    其妙
    1.39
     únicas
    1.39
     Europ
    1.39
    Activations Density 0.013%

    No Known Activations