© 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. 53034
    Prev
    Next
    INDEX
    Explanations

    hang updated

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

    netty, versions, timing

    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
    BlockUsed
    0.54
    MVCProject
    0.54
    MathMarks
    0.53
    EnglishMarks
    0.53
    乱流
    0.51
     الطلاب
    0.51
    解决方案
    0.50
    <unused65>
    0.50
    功率
    0.50
     دانشج
    0.50
    POSITIVE LOGITS
    0.57
     on
    0.54
     when
    0.54
     t
    0.53
    ↵↵
    0.53
     b
    0.52
     one
    0.52
     outer
    0.52
     d
    0.51
    @
    0.50
    Activations Density 0.000%

    No Known Activations