© 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. 212838
    Prev
    Next
    INDEX
    Explanations

    specific locations and instances

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

    examples, descriptions, or definitions

    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
    urs
    0.57
    ivní
    0.53
    čius
    0.51
    ح
    0.51
    AllFilesIn
    0.47
    ians
    0.47
    čí
    0.47
    Afghanistan
    0.47
    ierende
    0.46
     صرف
    0.45
    POSITIVE LOGITS
     hysterical
    0.54
     purported
    0.51
     Ecke
    0.51
     royalties
    0.48
     flimsy
    0.48
    엊
    0.48
    ತ್ತ
    0.48
     verbose
    0.47
    evu
    0.47
     turista
    0.46
    Activations Density 0.000%

    No Known Activations