© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 60660
    Prev
    Next
    INDEX
    Explanations

    properties and characteristics

    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_all/layer_41_width_262k_l0_big
    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
    用
    0.48
    Any
    0.45
    Expense
    0.45
    㳒
    0.43
    费
    0.43
     ఏద
    0.42
    作
    0.42
     جو
    0.41
    做
    0.41
    Lack
    0.41
    POSITIVE LOGITS
    getBlueTeam
    0.47
     ഉയ
    0.46
     corpse
    0.45
     ತಿಳಿದ
    0.44
     singleRun
    0.44
     shudder
    0.44
     yandan
    0.44
     forested
    0.43
    getRedTeam
    0.43
     middlemen
    0.43
    Activations Density 0.001%

    No Known Activations