© 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. 237450
    Prev
    Next
    INDEX
    Explanations

    special additional information

    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
    नई
    0.50
    os
    0.47
    ？！
    0.46
     cortar
    0.46
    on
    0.45
     companhia
    0.44
    从
    0.44
    மெ
    0.43
    真正的
    0.43
    ？？
    0.43
    POSITIVE LOGITS
     Необходимо
    0.53
     liens
    0.47
    ToAdd
    0.46
    윅
    0.45
     łyż
    0.45
     Кі
    0.45
     każ
    0.44
     unincorporated
    0.44
     Accommodation
    0.44
    слары
    0.43
    Activations Density 0.000%

    No Known Activations