© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 14489
    Prev
    Next
    INDEX
    Explanations

    Robert Jackson Lewis

    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
     cared
    1.42
     clust
    1.37
    frameNStart
    1.36
    ֡
    1.31
    ┍
    1.31
    الصف
    1.30
     cakkh
    1.30
    وسع
    1.27
     vuccati
    1.25
     تۆ
    1.24
    POSITIVE LOGITS
     পান
    1.11
     amea
    1.11
    "
    1.08
     প্রহ
    1.04
    𝐣
    1.03
     atras
    1.02
     piatto
    1.01
     amenazas
    0.99
     daño
    0.98
    ียร์
    0.98
    Activations Density 0.000%

    No Known Activations