© 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. 40-GEMMASCOPE-2-RES-262K
    7. 2586
    Prev
    Next
    INDEX
    Explanations

    initial scale, event handling, previews

    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_40_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
     Missy
    0.42
     glandes
    0.38
    𐰇
    0.37
    ষুধ
    0.36
     Hydrochloride
    0.35
     duckys
    0.35
     علیکم
    0.35
    玠
    0.35
    وبه
    0.34
    ঁচু
    0.34
    POSITIVE LOGITS
    S
    0.42
    s
    0.42
    ly
    0.40
    D
    0.39
    ing
    0.38
    id
    0.37
    и
    0.37
    i
    0.37
    I
    0.36
    ific
    0.36
    Activations Density 0.036%

    No Known Activations