© 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. 139002
    Prev
    Next
    INDEX
    Explanations

    running, breath, struggle, son, term, decreased

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

    phrases formed by token pairs

    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
     I
    0.51
     odpowiedzi
    0.51
     on
    0.48
     ș
    0.48
     riječi
    0.48
     county
    0.48
     amputation
    0.48
     字
    0.45
     ২৪
    0.45
     retrait
    0.45
    POSITIVE LOGITS
    湫
    0.47
     موجب
    0.46
     проведе
    0.46
    उंड
    0.45
    UnderWater
    0.45
    Парт
    0.45
    בית
    0.44
     Abstracts
    0.43
    instit
    0.43
    ச்சூழ
    0.43
    Activations Density 0.001%

    No Known Activations