© 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. 16-GEMMASCOPE-2-RES-262K
    7. 49389
    Prev
    Next
    INDEX
    Explanations

    static const

    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_16_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
    ali
    0.61
    B
    0.59
    ↵
    0.58
    fte
    0.57
    b
    0.57
    D
    0.56
    ed
    0.54
    ER
    0.53
    ken
    0.53
    S
    0.53
    POSITIVE LOGITS
     cheques
    0.56
    FBSDKGraph
    0.55
     synagogues
    0.55
    ность
    0.54
     cylinders
    0.54
     sniping
    0.53
    ქვს
    0.52
    ধানা
    0.50
     facades
    0.50
    際に
    0.50
    Activations Density 0.000%

    No Known Activations