© 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. 154662
    Prev
    Next
    INDEX
    Explanations

    burglar Friday, since my, would you

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

    specific impact or contract clauses

    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
    2
    0.47
    ता
    0.44
    continuous
    0.44
    significant
    0.43
    ۲۰
    0.42
    RED
    0.42
     prodigious
    0.42
     brisk
    0.42
     continuation
    0.41
     preso
    0.41
    POSITIVE LOGITS
    ឪ
    0.55
    不一样
    0.54
    ený
    0.54
     логи
    0.53
     Oba
    0.53
    党委
    0.52
     karane
    0.51
     шаблон
    0.51
     Eltern
    0.50
     অভিভাব
    0.50
    Activations Density 0.000%

    No Known Activations