© 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. 52101
    Prev
    Next
    INDEX
    Explanations

    finding pattern before specific following word

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

    concrete nouns and states

    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
    вшись
    0.48
    تی
    0.45
     gyr
    0.45
     latent
    0.43
    ぎ
    0.42
     sympathetic
    0.42
     bomber
    0.42
     بگ
    0.42
    надцать
    0.41
    DX
    0.41
    POSITIVE LOGITS
    畫面
    0.51
    ຊ
    0.49
     ಉಪ
    0.47
     θέση
    0.47
    azim
    0.46
    írez
    0.46
     五
    0.45
     पहु
    0.44
    二维
    0.44
     conteúdos
    0.44
    Activations Density 0.000%

    No Known Activations