© 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-65K
    7. 1230
    Prev
    Next
    INDEX
    Explanations

    time durations or points

    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_65k_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
    świet
    1.04
     której
    1.04
    ṓ
    1.02
    墠
    1.02
    zeczytaj
    1.02
     které
    1.02
     realizará
    1.02
     राकेश
    1.01
    VSLU
    1.01
    繖
    1.01
    POSITIVE LOGITS
     without
    1.24
     with
    1.20
     because
    1.19
     in
    1.06
     before
    1.00
     despite
    0.99
     when
    0.98
     throughout
    0.98
    without
    0.97
     from
    0.97
    Activations Density 1.072%

    No Known Activations