© 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. 13834
    Prev
    Next
    INDEX
    Explanations

    hence, providing explanations or results

    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
    ธ
    0.49
    誣
    0.49
    KOH
    0.45
    א
    0.45
    क
    0.44
    いたしました
    0.43
    ૫
    0.43
     სპეცი
    0.43
    ギ
    0.43
    ਓ
    0.43
    POSITIVE LOGITS
     payouts
    0.56
     example
    0.56
     because
    0.50
     happens
    0.49
     highlighted
    0.48
     explained
    0.46
     porque
    0.46
    因为
    0.46
     koska
    0.45
     bốn
    0.45
    Activations Density 0.137%

    No Known Activations