© 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. 136960
    Prev
    Next
    INDEX
    Explanations

    dosens of languages, crucial investment

    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
    чора
    0.43
    汎
    0.40
    情人
    0.39
    শাক
    0.38
    中有
    0.37
    不是
    0.37
    ੜ
    0.37
    pportun
    0.36
    睛
    0.36
    զ
    0.36
    POSITIVE LOGITS
     actitudes
    0.43
     reacciones
    0.39
     완성
    0.38
     aggi
    0.38
    ilación
    0.38
    ティーク
    0.37
    icoes
    0.37
     Lyons
    0.36
     Shih
    0.36
     additions
    0.35
    Activations Density 0.000%

    No Known Activations