© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 67119
    Prev
    Next
    INDEX
    Explanations

    listing items and continuing text

    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
    herent
    -1.08
    :&
    -1.04
    kommt
    -1.00
    ção
    -0.99
    corer
    -0.99
    tiche
    -0.97
    inafter
    -0.96
    urant
    -0.96
    ——”
    -0.96
    continence
    -0.95
    POSITIVE LOGITS
     should
    1.26
     could
    1.25
     can
    1.16
     would
    1.13
     may
    1.11
     باعث
    1.05
     we
    1.05
     likely
    1.02
     might
    1.02
     will
    1.01
    Activations Density 0.049%

    No Known Activations