© 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. 136901
    Prev
    Next
    INDEX
    Explanations

    open weights and implications

    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
    จร
    0.50
    ag
    0.46
    s
    0.44
    ↵
    0.44
    fought
    0.42
    นิด
    0.42
     Lordships
    0.42
    t
    0.42
    גו
    0.40
    god
    0.39
    POSITIVE LOGITS
     personales
    0.50
     കുടും
    0.48
     cambi
    0.47
     genealog
    0.46
     উপযুক্ত
    0.44
     personnelle
    0.44
     papi
    0.43
     henceforth
    0.43
     භාවිතා
    0.43
     عليه
    0.42
    Activations Density 0.003%

    No Known Activations