© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 37986
    Prev
    Next
    INDEX
    Explanations

    understanding luxury, monitoring, static

    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
    س
    0.55
     decays
    0.47
     contemporaries
    0.44
    ס
    0.43
    üb
    0.43
     strung
    0.43
     digested
    0.43
     Trat
    0.43
     schon
    0.42
    riere
    0.42
    POSITIVE LOGITS
    omot
    0.49
     mendatang
    0.46
    もっと
    0.44
    ते
    0.44
    ameva
    0.44
    ᑲ
    0.43
    ap
    0.43
    駕駛
    0.43
    9
    0.43
    avon
    0.43
    Activations Density 0.000%

    No Known Activations