© 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. 46335
    Prev
    Next
    INDEX
    Explanations

    car brands

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

    dialogue markers and specific names

    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
    мо
    0.57
    тер
    0.57
    ین
    0.56
    боре
    0.52
    ט
    0.52
    مد
    0.50
    Парт
    0.50
    ба
    0.50
    ّم
    0.50
    пет
    0.50
    POSITIVE LOGITS
     BB
    0.50
     Segunda
    0.49
     drugiej
    0.49
     B
    0.47
     modernist
    0.47
     Eli
    0.47
     Lexus
    0.47
     Honda
    0.46
     Toyota
    0.46
     INTEGR
    0.46
    Activations Density 0.000%

    No Known Activations