© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 14574
    Prev
    Next
    INDEX
    Explanations

    what you are doing or need help

    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
     nupt
    0.45
    മാനം
    0.39
     maze
    0.39
     amiable
    0.37
    firing
    0.37
     lawmaker
    0.36
    ክት
    0.36
    屬
    0.36
    おすすめ
    0.36
     informal
    0.35
    POSITIVE LOGITS
     accomplished
    0.49
    Doing
    0.46
     doing
    0.45
     done
    0.44
     accomplishing
    0.44
     DONE
    0.44
    doing
    0.42
    accompl
    0.42
     Doing
    0.42
    করেন
    0.41
    Activations Density 0.017%

    No Known Activations