© 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. 246078
    Prev
    Next
    INDEX
    Explanations

    daily, Ex, Station, condenser, occasionally, suspending

    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
     htmlFor
    0.45
     audition
    0.41
     výraz
    0.41
     aktor
    0.40
     blizzard
    0.40
    дные
    0.39
    $=
    0.38
     unending
    0.38
    ं
    0.37
     identifiers
    0.37
    POSITIVE LOGITS
     punishable
    0.47
     credited
    0.46
    宗旨
    0.46
     ಸರ್
    0.46
    equip
    0.45
    VOID
    0.44
     হলে
    0.44
     terrorist
    0.44
    সন্
    0.44
    撸
    0.43
    Activations Density 0.001%

    No Known Activations