© 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. 87816
    Prev
    Next
    INDEX
    Explanations

    Notes on, mg oral, actually happier

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

    widely used, features, strong

    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
    时
    0.47
     ponctu
    0.43
    ulières
    0.42
    仅
    0.41
    贤
    0.40
     annotations
    0.40
    不仅
    0.40
    为空
    0.40
     ヒ
    0.39
     περιο
    0.39
    POSITIVE LOGITS
    vect
    0.55
     NATO
    0.48
    ruptcy
    0.46
     гуляць
    0.45
    adays
    0.45
     चूंकि
    0.45
    htonl
    0.43
    Ꮧ
    0.43
    vod
    0.42
    ccd
    0.42
    Activations Density 0.000%

    No Known Activations