© 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. 123361
    Prev
    Next
    INDEX
    Explanations

    words to trust or answer

    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
    ಥವಾ
    0.50
    работ
    0.45
    зим
    0.45
    лето
    0.45
    новая
    0.45
    नाइटेड
    0.44
     complementing
    0.44
    ฐ
    0.44
     soundtracks
    0.44
     природ
    0.44
    POSITIVE LOGITS
     dys
    0.48
     vend
    0.46
     India
    0.44
     killed
    0.44
     who
    0.43
     intercourse
    0.43
     tavolo
    0.43
     unable
    0.42
     Buddhism
    0.42
     comrades
    0.42
    Activations Density 0.002%

    No Known Activations