© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7932
    Prev
    Next
    INDEX
    Explanations

    describing procedures as noninvasive

    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
     необхід
    -1.67
     ‘’
    -1.51
     frequ
    -1.39
     his
    -1.36
     their
    -1.30
    ąb
    -1.29
     gustó
    -1.27
     gustaba
    -1.25
     the
    -1.25
     hulk
    -1.24
    POSITIVE LOGITS
    ERS
    1.93
    帏
    1.47
    2
    1.43
    Feel
    1.37
    to
    1.35
     той
    1.34
     girasol
    1.30
    но
    1.30
    iyor
    1.27
     barri
    1.26
    Activations Density 0.101%

    No Known Activations