© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 66586
    Prev
    Next
    INDEX
    Explanations

    [concept] confusing/challenging

    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_22/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
     will
    -1.21
    を行い
    -1.02
     いち
    -0.99
     they
    -0.96
    就會
    -0.96
     wouldn
    -0.96
     couldn
    -0.94
     Burroughs
    -0.93
    側は
    -0.93
    的过程中
    -0.93
    POSITIVE LOGITS
     to
    1.73
     at
    1.16
     as
    1.10
     into
    1.07
     on
    1.02
     of
    1.00
    isasi
    0.96
     an
    0.96
    を
    0.95
     in
    0.92
    Activations Density 0.099%

    No Known Activations