© 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. 142007
    Prev
    Next
    INDEX
    Explanations

    hypothesis began

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

    copying or describing

    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
    ק
    0.44
    ાય
    0.43
    BROW
    0.43
    勇
    0.42
    세를
    0.41
     Worldwide
    0.41
    填写
    0.41
    링
    0.41
    Purch
    0.40
    악
    0.40
    POSITIVE LOGITS
     инфраструк
    0.52
     infrastrukt
    0.52
     οικο
    0.49
     hipótesis
    0.47
     যেন
    0.46
    hypothesis
    0.45
     begonnen
    0.45
     mendengar
    0.45
     ruhig
    0.45
    poč
    0.44
    Activations Density 0.004%

    No Known Activations