© 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. 219625
    Prev
    Next
    INDEX
    Explanations

    geographical regions

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

    Ukrainian military; pill split

    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
    abcdef
    0.45
    أة
    0.45
    ?]
    0.44
    يرة
    0.44
     calam
    0.44
    Жен
    0.43
    一个
    0.41
    ?");
    0.41
    ][%
    0.41
    ظم
    0.40
    POSITIVE LOGITS
     ಪ್ರದೇಶ
    0.50
     দেশটির
    0.47
    ouest
    0.46
     サイ
    0.45
     Oblast
    0.45
     ชาว
    0.44
    ◾
    0.44
     ಹಿಂದೆ
    0.44
     জানিয়েছে
    0.42
     प्रवासी
    0.42
    Activations Density 0.001%

    No Known Activations