© 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. 194091
    Prev
    Next
    INDEX
    Explanations

    novelists and poets

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

    internet lore

    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
    なわち
    0.47
    不下
    0.45
     向
    0.44
    がない
    0.43
    向上
    0.43
    屈
    0.43
     транс
    0.42
     斜
    0.42
    вай
    0.41
    在全球
    0.41
    POSITIVE LOGITS
     poets
    0.51
     poems
    0.50
    س
    0.48
     Poets
    0.46
     apie
    0.45
     poetry
    0.45
     filings
    0.45
     pracov
    0.45
     molyb
    0.44
     novelists
    0.44
    Activations Density 0.001%

    No Known Activations