© 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. 193822
    Prev
    Next
    INDEX
    Explanations

    sequence of specific tokens

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

    Validation, individual, shadow, scheduler, castle, single

    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
    Ⅺ
    0.53
     écailles
    0.52
    штар
    0.52
     Calyce
    0.51
     Tjiwarl
    0.50
     Onun
    0.50
     GoObject
    0.49
    ității
    0.48
    싼
    0.47
     крупных
    0.46
    POSITIVE LOGITS
     ein
    0.48
     เนื้อ
    0.47
     market
    0.46
     pok
    0.46
     jed
    0.46
     جب
    0.46
     hell
    0.45
     brilliance
    0.45
     dough
    0.43
    杰
    0.43
    Activations Density 0.000%

    No Known Activations