© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 213021
    Prev
    Next
    INDEX
    Explanations

    through a special partnership

    np_acts-logits-general · gemini-2.5-flash-lite

    focusing on research

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    不
    0.57
    故意
    0.49
    ಿ
    0.45
    生
    0.45
    年
    0.45
    金
    0.45
    但是
    0.44
    伯
    0.43
    之路
    0.43
    但在
    0.42
    POSITIVE LOGITS
    𝘢
    0.51
     escucha
    0.46
     मंद
    0.46
    اديه
    0.45
    ᓃ
    0.45
    花の
    0.44
    pada
    0.44
     atraves
    0.44
     Presidente
    0.44
     triglycerides
    0.44
    Activations Density 0.001%

    No Known Activations