© 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. 14929
    Prev
    Next
    INDEX
    Explanations

    years and digits

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

    "I" followed by specific punctuation or words

    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
     весьма
    0.63
     tačiau
    0.52
     当然
    0.52
     azonban
    0.51
    事实上
    0.49
     столь
    0.47
     insofar
    0.46
    倘
    0.46
     কিংবা
    0.45
    最为
    0.45
    POSITIVE LOGITS
     २०२
    0.73
     ২০২২
    0.73
     २०२२
    0.66
    🥰
    0.65
     ২০২৩
    0.65
     проєкту
    0.64
     проє
    0.59
    TikTok
    0.59
     ২০২১
    0.58
    covid
    0.56
    Activations Density 0.038%

    No Known Activations