© 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. 64651
    Prev
    Next
    INDEX
    Explanations

    location or state

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

    many students

    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
    บัน
    0.51
    Record
    0.46
     होनी
    0.45
     tastings
    0.45
    暾
    0.45
    Mongo
    0.44
     เขียน
    0.44
    䏌
    0.44
     spice
    0.44
     งาน
    0.43
    POSITIVE LOGITS
    َل
    0.52
    мерикан
    0.46
     ۲
    0.46
     Hintergrund
    0.45
    mph
    0.45
     Shops
    0.44
    reate
    0.43
    äub
    0.42
    لما
    0.42
    ません
    0.42
    Activations Density 0.000%

    No Known Activations