© 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. 190188
    Prev
    Next
    INDEX
    Explanations

    discussing concepts

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

    standing at heights

    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
     postseason
    0.49
    ilità
    0.47
    டும்ப
    0.46
     мог
    0.46
    ｉ
    0.46
    scheduling
    0.46
     βασ
    0.46
     preseason
    0.46
    थाम
    0.46
     mattered
    0.46
    POSITIVE LOGITS
     enfant
    0.61
     و
    0.56
     جوړونکي
    0.52
     ح
    0.51
     Boutique
    0.51
     Consultant
    0.50
     Tonic
    0.49
     Atelier
    0.49
     ك
    0.49
     ر
    0.49
    Activations Density 0.001%

    No Known Activations