© 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. 216647
    Prev
    Next
    INDEX
    Explanations

    summer months

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

    authority, jam, search, common, practical

    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
     world
    0.50
     =
    0.44
     submarine
    0.44
     seawater
    0.44
     sea
    0.43
    世界
    0.43
     העולם
    0.42
     maintained
    0.42
     curtain
    0.41
     Namibia
    0.41
    POSITIVE LOGITS
    dens
    0.50
    блоки
    0.46
    緎
    0.46
    िग
    0.46
    diversity
    0.44
    сторія
    0.44
    jších
    0.43
    ジオ
    0.43
     fxg
    0.43
    жны
    0.43
    Activations Density 0.001%

    No Known Activations