© 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. 199559
    Prev
    Next
    INDEX
    Explanations

    natural ingredients, process, practice

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

    code portability and babies

    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
    欹
    0.46
    답
    0.42
    pinimg
    0.40
     их
    0.40
     avenues
    0.40
    꼐
    0.40
     drawings
    0.39
    inqu
    0.39
    도
    0.39
     polynucle
    0.39
    POSITIVE LOGITS
     ✅
    0.46
     poveć
    0.44
     (+
    0.43
     dédié
    0.43
    🥥
    0.42
     extracción
    0.42
     स्तन
    0.40
    </tr>
    0.40
     Первый
    0.39
    セキュリティ
    0.39
    Activations Density 0.000%

    No Known Activations