© 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. 76600
    Prev
    Next
    INDEX
    Explanations

    watching 👀

    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
    rejected
    0.46
    वा
    0.45
    چ
    0.43
    ax
    0.43
    ور
    0.42
    um
    0.41
    robust
    0.41
    ブ
    0.41
    dynamic
    0.40
    BAN
    0.40
    POSITIVE LOGITS
     Margin
    0.46
     Donor
    0.45
     Donate
    0.45
     Abit
    0.44
     donating
    0.44
     Rating
    0.43
     Volvo
    0.43
     graag
    0.43
     rect
    0.43
     ули
    0.43
    Activations Density 0.001%

    No Known Activations