© 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. 8534
    Prev
    Next
    INDEX
    Explanations

    exercise or physical descriptions

    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
    落
    0.57
    更好地
    0.46
     Equitable
    0.46
    人
    0.45
     समकक्ष
    0.44
    府
    0.44
    更好
    0.43
    ικής
    0.43
    片
    0.43
    Foreground
    0.42
    POSITIVE LOGITS
     cams
    0.53
     camo
    0.47
    uche
    0.46
     predictor
    0.46
     trailing
    0.45
     ஒன்றை
    0.45
     எதிர்க
    0.45
     duas
    0.45
    ಾಗ್
    0.44
     ADMIN
    0.43
    Activations Density 0.005%

    No Known Activations