© 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-65K
    7. 13036
    Prev
    Next
    INDEX
    Explanations

    this is a

    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_65k_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
     этого
    0.56
    }^*
    0.52
     цього
    0.52
     هذا
    0.51
     этому
    0.50
    ນີ້
    0.50
     tohoto
    0.49
     diesen
    0.49
     dieses
    0.49
     этих
    0.48
    POSITIVE LOGITS
    我的
    0.54
     a
    0.50
     een
    0.48
    lą
    0.47
     ஓர்
    0.47
     μια
    0.44
     eine
    0.44
    </tbody>
    0.43
    プレ
    0.43
     an
    0.43
    Activations Density 0.054%

    No Known Activations