© 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. 122584
    Prev
    Next
    INDEX
    Explanations

    handling, design, and good times

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

    comparisons and alternatives

    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
    लॉक
    0.53
    କ
    0.53
    К
    0.50
    ક
    0.49
    ફ
    0.49
    お
    0.47
    iqués
    0.46
    奉
    0.45
    cklen
    0.45
    கோ
    0.45
    POSITIVE LOGITS
     لفظ
    0.50
    تری
    0.44
     sacc
    0.43
    Paged
    0.42
     совокуп
    0.42
     одному
    0.42
     współ
    0.42
     مشتمل
    0.42
    လျှ
    0.42
     nhiệt
    0.42
    Activations Density 0.000%

    No Known Activations