© 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. 48457
    Prev
    Next
    INDEX
    Explanations

    interact with

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

    capital letters

    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
     jazy
    0.55
    ních
    0.49
     především
    0.48
     hoera
    0.47
     danych
    0.47
    存储
    0.46
    桃
    0.45
    ეტ
    0.43
     gespe
    0.43
     Zuid
    0.43
    POSITIVE LOGITS
    ل
    0.56
    oliath
    0.52
    WAM
    0.48
    acre
    0.48
    г
    0.47
    و
    0.46
    있
    0.44
    omonas
    0.43
     Insulation
    0.42
    க்கொண்டு
    0.42
    Activations Density 0.001%

    No Known Activations