© 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. 194327
    Prev
    Next
    INDEX
    Explanations

    long lineups

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

    committed elements costs

    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
     પાણી
    0.57
    Sebagai
    0.53
     તેનું
    0.51
    Penumpang
    0.51
     акчага
    0.50
     ગે
    0.50
     કાર્
    0.49
    ૩
    0.49
    venir
    0.49
     તેનો
    0.49
    POSITIVE LOGITS
     quizzes
    0.50
     regularity
    0.47
    าตุ
    0.47
     customizing
    0.46
    机
    0.45
     semester
    0.44
     formalism
    0.44
     vacc
    0.44
     spelled
    0.43
    ാരി
    0.43
    Activations Density 0.001%

    No Known Activations