© 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. 40-GEMMASCOPE-2-RES-262K
    7. 120322
    Prev
    Next
    INDEX
    Explanations

    operations on calculations

    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_40_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
    干部
    0.44
     washers
    0.40
     katt
    0.39
     अंसारी
    0.38
    鋃
    0.37
     abrasion
    0.37
     washer
    0.36
    お届け
    0.36
    ބ
    0.36
     ابراہیم
    0.35
    POSITIVE LOGITS
     comb
    0.44
    存档
    0.43
     supervis
    0.40
     niem
    0.40
     si
    0.38
     recipe
    0.38
    Vars
    0.38
     privacidade
    0.37
     wn
    0.37
    recipe
    0.37
    Activations Density 0.001%

    No Known Activations