© 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
    2. Gemma-3-27B-IT
    3. 41-GEMMASCOPE-2-RES-262K
    4. 30759
    Prev
    Next
    INDEX
    Explanations

    flag 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_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
     adopté
    0.37
     redox
    0.36
     rejection
    0.36
    áu
    0.36
    गुड
    0.35
     definitions
    0.35
    स्‍त
    0.35
    硞
    0.35
    IPT
    0.35
     cottage
    0.35
    POSITIVE LOGITS
    artha
    0.40
    Ra
    0.40
    AllRef
    0.40
    Wish
    0.37
    莎
    0.37
     Wish
    0.37
    叉
    0.37
    ում
    0.36
     cinerea
    0.36
     wish
    0.36
    Activations Density 0.014%

    No Known Activations