© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 21611
    Prev
    Next
    INDEX
    Explanations

    financial terms and values

    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
    栊
    -1.82
     både
    -1.76
     mey
    -1.70
    .},
    -1.65
    ference
    -1.64
    šku
    -1.60
    .~\
    -1.59
    actéristi
    -1.57
     Coconut
    -1.56
    —–
    -1.55
    POSITIVE LOGITS
     from
    3.14
     for
    2.22
     at
    2.17
    It
    1.98
     in
    1.95
     as
    1.90
     without
    1.88
    There
    1.81
     around
    1.79
     before
    1.77
    Activations Density 0.014%

    No Known Activations