© 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. 59453
    Prev
    Next
    INDEX
    Explanations

    specific noun modifiers

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

    AI, PostgreSQL, file, market, light, writing

    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
    س
    0.62
    s
    0.60
    ت
    0.49
    স
    0.49
    ти
    0.48
    स
    0.48
    Ink
    0.47
    Economics
    0.47
    퍽
    0.46
    с
    0.45
    POSITIVE LOGITS
     fiancé
    0.52
     sleepy
    0.52
     dau
    0.50
     غذ
    0.50
     foreman
    0.50
     silicone
    0.50
     doo
    0.49
     mocha
    0.49
     gay
    0.49
    entuan
    0.49
    Activations Density 0.000%

    No Known Activations