© 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. 248904
    Prev
    Next
    INDEX
    Explanations

    words preceding common collocations

    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
    一個
    0.46
    NJ
    0.45
    虞
    0.45
    辛苦
    0.44
    等待
    0.43
    乗
    0.43
     지나
    0.42
    곧
    0.42
    結婚
    0.42
    強化
    0.42
    POSITIVE LOGITS
     phénomène
    0.49
     fenómenos
    0.47
     informes
    0.47
     fenómeno
    0.47
     ambientales
    0.46
     cuenta
    0.46
     Kodi
    0.45
     породы
    0.45
     отлично
    0.44
    рена
    0.44
    Activations Density 0.000%

    No Known Activations