© 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. 16-GEMMASCOPE-2-RES-262K
    7. 86137
    Prev
    Next
    INDEX
    Explanations

    Pentagon events

    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_16_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
     మాట్లాడుతూ
    0.56
     เงี้ย
    0.55
    gypt
    0.55
    ernen
    0.54
     Германия
    0.54
     ਸਿੰ
    0.53
     گلوکار
    0.53
    豎
    0.52
    テナンス
    0.52
    特集
    0.49
    POSITIVE LOGITS
     allotments
    0.48
     Atlantic
    0.48
     (
    0.47
     vegetables
    0.47
     races
    0.46
     lettuce
    0.46
     Imp
    0.46
     tomatoes
    0.46
     shank
    0.45
     flavours
    0.45
    Activations Density 0.000%

    No Known Activations