© 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. 135564
    Prev
    Next
    INDEX
    Explanations

    language diversity

    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
    山区
    0.51
    StaticHandler
    0.51
    ेंटिस
    0.45
    Miscellaneous
    0.45
    (".");
    0.44
     திரும
    0.43
    ="";
    0.43
    iderman
    0.43
    ักษณะ
    0.42
    ("");
    0.42
    POSITIVE LOGITS
     baskets
    0.46
     newest
    0.45
     தங்கள்
    0.45
     لاءِ
    0.45
     who
    0.44
     którzy
    0.44
     σο
    0.43
     times
    0.42
     μεγά
    0.42
     their
    0.42
    Activations Density 0.002%

    No Known Activations