© 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. 142154
    Prev
    Next
    INDEX
    Explanations

    connection stream

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

    lists or specific nouns

    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
     pavimento
    0.56
     fluvial
    0.53
     há
    0.51
     soal
    0.50
     imasmim
    0.50
     ó
    0.49
     combate
    0.49
     rì
    0.49
     hac
    0.49
     clima
    0.48
    POSITIVE LOGITS
    ستی
    0.54
    국
    0.54
    凤凰
    0.53
    호를
    0.53
    ಬ
    0.52
    ח
    0.52
    less
    0.51
    Celebrate
    0.50
    ب
    0.50
    It
    0.50
    Activations Density 0.000%

    No Known Activations