© 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. 104319
    Prev
    Next
    INDEX
    Explanations

    causes quarrels

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

    specialized locations and items

    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
     продав
    0.52
     велико
    0.51
    д
    0.51
     восстановления
    0.50
     синте
    0.50
     ক্ষয়
    0.49
     スタッドレスタイヤ
    0.49
     Miro
    0.49
    лд
    0.48
    <unused406>
    0.48
    POSITIVE LOGITS
    sc
    0.47
     humus
    0.47
    SA
    0.45
     place
    0.44
     tiered
    0.44
     Spotted
    0.44
     flick
    0.44
     ip
    0.44
     ier
    0.44
     armband
    0.43
    Activations Density 0.000%

    No Known Activations