© 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. 72031
    Prev
    Next
    INDEX
    Explanations

    approve non-resident agreements

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

    states entities

    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
     יכול
    0.58
     podía
    0.48
    几何
    0.48
    fähig
    0.45
    );\
    0.44
    ij
    0.42
     ניתן
    0.42
     substit
    0.42
     $\{$
    0.41
    ,\\
    0.41
    POSITIVE LOGITS
    ائیں۔
    0.54
    ｱ
    0.52
    Мы
    0.51
    ആ
    0.51
    Этот
    0.51
    ✞
    0.49
    АН
    0.49
    チャー
    0.49
    και
    0.48
    Ⴝ
    0.47
    Activations Density 0.001%

    No Known Activations