© 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. 55512
    Prev
    Next
    INDEX
    Explanations

    special conjunctions and qualifiers

    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
     کہاں
    0.53
    embry
    0.41
     będ
    0.39
    чора
    0.39
    eraser
    0.38
     kemarin
    0.38
     ব্যপারে
    0.38
    婁
    0.38
    で見
    0.38
    滁
    0.38
    POSITIVE LOGITS
    ៥
    0.43
    “,
    0.43
    ²,
    0.41
    »,
    0.40
     коле
    0.40
     desolate
    0.40
    เป็น
    0.39
     ఒకటి
    0.38
     statistic
    0.38
    achelorette
    0.38
    Activations Density 0.009%

    No Known Activations