© 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. 138887
    Prev
    Next
    INDEX
    Explanations

    non-english characters

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

    replacing informal words

    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
     catalysis
    0.50
     ደ
    0.45
     स
    0.45
    ien
    0.44
     使い
    0.44
     ژ
    0.44
     フォー
    0.44
    藺
    0.44
     ነ
    0.43
     قیمت
    0.43
    POSITIVE LOGITS
     fiume
    0.54
    deload
    0.52
    衝突
    0.49
    ውስ
    0.47
    DROP
    0.45
    W
    0.45
    ব
    0.44
    buton
    0.43
    대전
    0.43
    었습니다
    0.43
    Activations Density 0.000%

    No Known Activations