© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 143478
    Prev
    Next
    INDEX
    Explanations

    structure and definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     câștig
    0.58
     physiologic
    0.55
     olympiques
    0.55
     dị
    0.54
    鉑
    0.54
     sanguí
    0.53
     iniziale
    0.52
     inför
    0.52
     դ
    0.52
     నాలుగు
    0.52
    POSITIVE LOGITS
    UTF
    0.46
    An
    0.46
    iten
    0.45
    Column
    0.45
     UTF
    0.44
    I
    0.44
     Column
    0.42
    。
    0.42
    allows
    0.42
    seriously
    0.42
    Activations Density 0.000%

    No Known Activations