© 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. 151845
    Prev
    Next
    INDEX
    Explanations

    guide and vision

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

    blocks vs. write

    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
    ún
    0.52
    alé
    0.50
    š
    0.49
    ş
    0.48
    的总
    0.48
    ém
    0.47
    +"
    0.47
     (
    0.45
    ované
    0.45
    的可
    0.45
    POSITIVE LOGITS
    淘
    0.48
     injurious
    0.47
    LIFE
    0.47
    یو
    0.47
    یع
    0.46
    smtp
    0.45
     আহ্ব
    0.45
    琺
    0.45
    ッテ
    0.45
    โจ
    0.44
    Activations Density 0.000%

    No Known Activations