© 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. 136339
    Prev
    Next
    INDEX
    Explanations

    niche, limb, dry

    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
    oxy
    0.42
    gaxModule
    0.38
    krét
    0.37
    scp
    0.36
    缺
    0.36
    прочем
    0.35
     multiport
    0.35
     pouvaient
    0.35
    xym
    0.35
     thom
    0.35
    POSITIVE LOGITS
     ανε
    0.37
    涤
    0.37
    하기
    0.36
     saada
    0.36
    كات
    0.35
    κη
    0.34
    YT
    0.33
     ā
    0.33
     gravit
    0.33
    Mechanical
    0.33
    Activations Density 0.000%

    No Known Activations