© 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. 11436
    Prev
    Next
    INDEX
    Explanations

    | By Author

    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
    -
    0.68
    ônio
    0.54
    ợi
    0.52
    чины
    0.51
     يك
    0.49
    ='
    0.48
    ጠን
    0.48
    ры
    0.47
    원
    0.46
    ξ
    0.46
    POSITIVE LOGITS
     లేదా
    0.50
     rask
    0.49
     bj
    0.47
     kredit
    0.46
     x
    0.45
     ბ
    0.45
     james
    0.45
    earned
    0.44
     |.
    0.44
     seni
    0.44
    Activations Density 0.001%

    No Known Activations