© 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. 211617
    Prev
    Next
    INDEX
    Explanations

    sanctions, nation, habits, stronger, came

    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
    穼
    0.41
     dís
    0.40
    锢
    0.40
    Appellant
    0.39
     reagents
    0.39
    嬅
    0.39
    记载
    0.38
     കിട
    0.38
    ܢܐ
    0.38
    密钥
    0.38
    POSITIVE LOGITS
    W
    0.44
    M
    0.42
    R
    0.42
     debilitating
    0.42
     мяс
    0.41
    H
    0.40
    rita
    0.39
     си
    0.39
    Си
    0.39
     Си
    0.39
    Activations Density 0.001%

    No Known Activations