© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 208868
    Prev
    Next
    INDEX
    Explanations

    will be, came back, brace ourselves

    np_acts-logits-general · gemini-2.5-flash-lite

    accomplishment, driver, family, trunk

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ")
    0.50
     gouttes
    0.47
    亗
    0.44
    ?
    0.43
    .___
    0.42
    脿
    0.42
    iz
    0.42
    /
    0.41
    楽天市場
    0.41
    性
    0.41
    POSITIVE LOGITS
     Healing
    0.45
    蘞
    0.44
     hybridized
    0.44
     Sculpture
    0.43
     startGame
    0.43
     Dock
    0.43
     Ontology
    0.43
     methodName
    0.42
     applicationId
    0.42
     Changes
    0.41
    Activations Density 0.000%

    No Known Activations