© 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. 31-GEMMASCOPE-2-RES-262K
    7. 75750
    Prev
    Next
    INDEX
    Explanations

    multi-lingual and specialized terms

    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_31_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
    ников
    0.55
    uretic
    0.47
    x
    0.46
     misery
    0.46
    kins
    0.45
    採用
    0.45
     vanity
    0.45
    nosť
    0.44
    nikov
    0.44
    ยนต์
    0.43
    POSITIVE LOGITS
    澍
    0.50
     ataques
    0.46
    原始内容存档
    0.45
    专属
    0.44
     અલગ
    0.44
     Fácil
    0.43
    လား
    0.42
     crea
    0.42
     tạo
    0.42
     Huz
    0.42
    Activations Density 0.002%

    No Known Activations