© 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. 16-GEMMASCOPE-2-RES-262K
    7. 48839
    Prev
    Next
    INDEX
    Explanations

    rubber or PEM format

    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_16_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
    ட்
    0.65
    น
    0.64
    ਡ
    0.64
    с
    0.64
    ຄວາມ
    0.61
    из
    0.61
    a
    0.61
    एस्ट
    0.60
     inconven
    0.60
    salted
    0.60
    POSITIVE LOGITS
    적인
    0.63
     on
    0.62
     Smartphone
    0.59
    ية
    0.58
    elijke
    0.58
     Bevölkerung
    0.58
     Television
    0.57
    ำ
    0.54
     infrastructure
    0.53
     Fishing
    0.53
    Activations Density 0.000%

    No Known Activations