© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 126051
    Prev
    Next
    INDEX
    Explanations

    open weights model

    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
     광
    0.61
    চর্
    0.57
    கொ
    0.57
    িন
    0.56
     equipos
    0.55
     tolu
    0.55
    ផ្ស
    0.54
    เป็น
    0.54
    y
    0.51
     ofere
    0.50
    POSITIVE LOGITS
    지
    0.54
    ሽታ
    0.51
    ?
    0.50
    ες
    0.49
     Vigil
    0.49
    人事
    0.48
     ricordo
    0.47
    was
    0.47
     विषय
    0.47
     a
    0.46
    Activations Density 0.031%

    No Known Activations