© 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. 2739
    Prev
    Next
    INDEX
    Explanations

    or

    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
     dành
    0.41
     చేయడానికి
    0.38
     mécanismes
    0.37
    বেই
    0.34
     ఇతర
    0.34
    ுகிறார்கள்
    0.34
     mediates
    0.33
    ᐟ
    0.33
     Town
    0.33
     virulence
    0.33
    POSITIVE LOGITS
    或
    0.55
    หรือ
    0.55
     или
    0.49
    和
    0.48
     किंवा
    0.46
     ಅಥವಾ
    0.46
     અથવા
    0.44
     أو
    0.43
     或
    0.43
     or
    0.43
    Activations Density 0.109%

    No Known Activations