© 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. 13674
    Prev
    Next
    INDEX
    Explanations

    HTML line breaks

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

    HTML input and labels

    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
    чках
    0.47
     banal
    0.45
    隴
    0.42
    美麗
    0.42
     второго
    0.41
    angal
    0.41
     stunted
    0.41
    樁
    0.41
     약
    0.40
    一個
    0.40
    POSITIVE LOGITS
    ↵↵
    0.42
    :“
    0.42
    ius
    0.40
    lah
    0.40
     HOWEVER
    0.39
    ches
    0.39
     roving
    0.39
    ísimo
    0.39
    THAT
    0.39
    🚐
    0.39
    Activations Density 0.000%

    No Known Activations