© 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. 69876
    Prev
    Next
    INDEX
    Explanations

    composed or not

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

    step-by-step process

    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
     pepp
    0.42
    দম
    0.41
     boasted
    0.41
     minimal
    0.40
     двох
    0.40
     gr
    0.39
     suporte
    0.39
    C
    0.39
    St
    0.39
    Don
    0.39
    POSITIVE LOGITS
    ladi
    0.42
    ленную
    0.39
     Prius
    0.39
     ಮತ್ತೆ
    0.38
    ทยา
    0.38
     본격
    0.38
     ار
    0.37
    になります
    0.37
    hyde
    0.37
    rowave
    0.37
    Activations Density 0.000%

    No Known Activations