© 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. 211568
    Prev
    Next
    INDEX
    Explanations

    not used

    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
    ங்கரை
    0.42
     ⚫
    0.39
    ड़की
    0.38
     hasonló
    0.38
     দেয়
    0.38
     yena
    0.36
     gewoon
    0.36
    ⚫
    0.36
    sebastian
    0.36
     وفر
    0.36
    POSITIVE LOGITS
    NOT
    0.50
    Not
    0.44
    not
    0.41
    Images
    0.41
     Moves
    0.41
     Greenberg
    0.40
     नही
    0.39
    使用
    0.39
     Images
    0.39
     Not
    0.39
    Activations Density 0.003%

    No Known Activations