© 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. 84221
    Prev
    Next
    INDEX
    Explanations

    fee and upfront payments

    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
    聸
    0.41
     embroidery
    0.40
     rods
    0.40
     streaks
    0.40
     residues
    0.39
     surname
    0.39
    ضة
    0.38
    刺繍
    0.38
     exchangers
    0.38
    ục
    0.38
    POSITIVE LOGITS
     LGA
    0.39
     Improving
    0.39
     Î
    0.38
     설
    0.38
     Нужно
    0.37
    垲
    0.37
     فح
    0.37
     હા
    0.36
    我对
    0.36
     너
    0.36
    Activations Density 0.000%

    No Known Activations