© 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. 228705
    Prev
    Next
    INDEX
    Explanations

    terms, performance, wire, desperate

    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
    ώ
    0.52
     vezes
    0.45
     Vis
    0.44
     várias
    0.44
    놈
    0.43
     smooth
    0.43
     funny
    0.43
    ỗi
    0.43
     mío
    0.43
    핑
    0.43
    POSITIVE LOGITS
     সাম্প্রতিক
    0.52
     আলোচনার
    0.51
    Begriff
    0.50
    ления
    0.50
     เอ
    0.50
    structor
    0.47
    ক
    0.47
     ฉาก
    0.47
     सहमति
    0.46
    oleum
    0.46
    Activations Density 0.006%

    No Known Activations