© 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. 170093
    Prev
    Next
    INDEX
    Explanations

    jsjda

    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
     stimuli
    0.46
    *********
    0.46
    天氣
    0.45
    AMP
    0.45
    ಡಿಯ
    0.44
    avkhat
    0.44
    駑
    0.44
    遷
    0.43
     Along
    0.43
     விருது
    0.43
    POSITIVE LOGITS
    it
    0.55
     dovrebbe
    0.49
    atore
    0.44
     possibili
    0.43
    fact
    0.41
     asal
    0.41
    on
    0.40
     should
    0.40
     élarg
    0.40
     geniş
    0.40
    Activations Density 0.001%

    No Known Activations