© 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. 65048
    Prev
    Next
    INDEX
    Explanations

    vertex shader

    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
    郎
    0.40
     Sty
    0.37
     Mari
    0.37
     Remed
    0.36
     wag
    0.36
     undeniably
    0.35
    cred
    0.35
    胞
    0.35
     **/
    0.35
     conco
    0.34
    POSITIVE LOGITS
     granit
    0.47
    setupUi
    0.47
    emitting
    0.45
    setInput
    0.44
    Primitive
    0.44
    rizable
    0.43
    Emit
    0.43
     rink
    0.43
     granulation
    0.43
    Delivery
    0.42
    Activations Density 0.002%

    No Known Activations