© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 2397
    Prev
    Next
    INDEX
    Explanations

    ground, land, desert, hole

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_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
    曲
    2.04
    ウィンドウ
    1.97
    تدائي
    1.96
    шымта
    1.92
     binoculars
    1.91
    elhos
    1.90
    돛
    1.89
    omers
    1.85
     panes
    1.85
     erythe
    1.84
    POSITIVE LOGITS
     loam
    1.95
    stepping
    1.88
     rooting
    1.88
    rock
    1.75
    मिताभ
    1.72
    垫
    1.67
     terre
    1.67
     root
    1.65
     Steep
    1.65
    ючись
    1.64
    Activations Density 1.135%

    No Known Activations