© 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. 57743
    Prev
    Next
    INDEX
    Explanations

    are quite

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

    multilingual phrases and numerical axes

    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
    ס
    0.49
    ర్లు
    0.47
    蟶
    0.46
    స్
    0.45
    Obst
    0.45
    Ố
    0.44
     ironically
    0.42
    ："
    0.42
    عرض
    0.42
    리
    0.42
    POSITIVE LOGITS
     வெற்றிய
    0.45
     වශ
    0.42
    reducer
    0.42
    lä
    0.42
     الماده
    0.41
    ረጃ
    0.40
    டன்
    0.40
    年在
    0.40
     চালিয়ে
    0.40
     reducer
    0.39
    Activations Density 0.000%

    No Known Activations