© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 6083
    Prev
    Next
    INDEX
    Explanations

    programming keywords and syntax

    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
    া
    2.80
    point
    2.53
    ாட
    2.50
    boards
    2.36
    ্কর
    2.35
    ؤں
    2.26
    े
    2.25
    ugh
    2.23
    werp
    2.18
    ktiv
    2.18
    POSITIVE LOGITS
    s
    3.66
    もら
    3.03
    ات
    3.00
    etown
    2.96
    いる
    2.68
    น์
    2.59
    র
    2.54
    隍
    2.49
    ्ञ
    2.49
    siye
    2.48
    Activations Density 1.570%

    No Known Activations