© 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. 83748
    Prev
    Next
    INDEX
    Explanations

    If you

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

    menus and options

    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
     posits
    0.47
    it
    0.47
     kuti
    0.47
    劣化
    0.45
     headquartered
    0.43
     fintech
    0.42
     reflects
    0.41
    ൽ
    0.41
     architectures
    0.41
     produces
    0.40
    POSITIVE LOGITS
     ಮತ್ತೆ
    0.47
    總
    0.46
    獨
    0.45
     आरमार
    0.45
     மற்றொரு
    0.44
     прошлом
    0.44
     勺
    0.44
    獎
    0.44
     독
    0.43
    ाना
    0.43
    Activations Density 0.004%

    No Known Activations