© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 53-GEMMASCOPE-2-RES-262K
    7. 64575
    Prev
    Next
    INDEX
    Explanations

    and Italian

    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_53_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
     sequentially
    0.48
     ACTIVE
    0.40
     synchronous
    0.40
     Chương
    0.40
    ⑸
    0.40
     accum
    0.39
     conformal
    0.39
    chas
    0.38
    দিনের
    0.38
     парази
    0.38
    POSITIVE LOGITS
     intérêt
    0.41
    </blockquote>
    0.41
    毒
    0.39
    </h2>
    0.39
     original
    0.39
     tk
    0.37
     Nova
    0.37
     premi
    0.37
     premiere
    0.36
     ț
    0.36
    Activations Density 0.001%

    No Known Activations