© 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. 12595
    Prev
    Next
    INDEX
    Explanations

    by or through

    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
     gustado
    -0.97
    dillo
    -0.96
    vět
    -0.95
    」,
    -0.93
     testigo
    -0.93
    andaag
    -0.91
     fará
    -0.90
    ított
    -0.90
    idelberg
    -0.90
    τικής
    -0.89
    POSITIVE LOGITS
     by
    2.55
     through
    2.08
     poprzez
    2.03
     mediante
    2.02
     bằng
    1.83
     путем
    1.73
     via
    1.63
     באמצעות
    1.60
     includes
    1.55
     include
    1.51
    Activations Density 0.067%

    No Known Activations