© 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. 57084
    Prev
    Next
    INDEX
    Explanations

    be with

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

    flour, workouts, filler rod

    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
    کار
    0.43
     olmadan
    0.42
     környez
    0.40
    ?!?
    0.40
    ل
    0.40
    ？
    0.40
     addirittura
    0.40
     கமல்ஹா
    0.40
    킹
    0.39
     nélkül
    0.39
    POSITIVE LOGITS
     calmly
    0.43
     BEAUT
    0.43
     GABA
    0.42
    ushi
    0.42
     supervisor
    0.41
     supervisors
    0.41
     TAKE
    0.41
     जबाब
    0.41
     disobey
    0.41
     আসিয়া
    0.41
    Activations Density 0.000%

    No Known Activations