© 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. 133742
    Prev
    Next
    INDEX
    Explanations

    download now

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

    impactful and important descriptions

    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
    歴
    0.48
     birdies
    0.47
    ↵
    0.44
     }//
    0.42
     CGRect
    0.41
     OnePlus
    0.40
     તેમજ
    0.40
     bullion
    0.40
     stats
    0.40
    CFBundle
    0.40
    POSITIVE LOGITS
     aument
    0.48
     можна
    0.47
    nak
    0.47
    कुंड
    0.46
     pessoa
    0.46
    ческой
    0.45
     lze
    0.45
     apparaît
    0.44
    瞽
    0.44
    лка
    0.44
    Activations Density 0.001%

    No Known Activations