© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 90748
    Prev
    Next
    INDEX
    Explanations

    responsible for, probability of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    бері
    0.47
     майже
    0.46
    فی
    0.45
    „
    0.45
     расчет
    0.44
    ственных
    0.43
    onnées
    0.43
    teness
    0.43
    ಪ್ಪು
    0.42
    깽
    0.42
    POSITIVE LOGITS
     telephones
    0.53
     vives
    0.51
     atmosfera
    0.50
     trajectories
    0.49
     piqu
    0.49
     dampers
    0.49
     Dalmat
    0.48
     weekdays
    0.47
     viva
    0.47
     caminando
    0.46
    Activations Density 0.001%

    No Known Activations