© 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. 34533
    Prev
    Next
    INDEX
    Explanations

    already started

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

    sapbowinto

    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
    鿁
    0.46
    seign
    0.45
    ურ
    0.45
    개의
    0.43
     అంశ
    0.43
     fejl
    0.43
    िक्त
    0.43
     जब्त
    0.43
     Ressourcen
    0.43
     baisse
    0.42
    POSITIVE LOGITS
    各自
    0.46
     zucchero
    0.45
    obic
    0.45
     比
    0.44
     aiutare
    0.44
    疲
    0.44
     tabs
    0.43
    DI
    0.43
     aiuta
    0.43
    atility
    0.42
    Activations Density 0.000%

    No Known Activations