© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 40435
    Prev
    Next
    INDEX
    Explanations

    tasks, diaspora, than

    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
    கோ
    0.44
     வடக்கு
    0.42
    ĥ
    0.42
     Saccharomyces
    0.38
     izvr
    0.38
    Ī
    0.38
     Nevada
    0.38
    Gol
    0.38
    ഒ
    0.38
     виконання
    0.37
    POSITIVE LOGITS
    动的
    0.44
     pedibus
    0.43
     상담
    0.39
    просы
    0.39
    掊
    0.38
    ữu
    0.38
    绑定
    0.38
    atenate
    0.37
     برابر
    0.37
    涉及到
    0.37
    Activations Density 0.009%

    No Known Activations