© 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. 842
    Prev
    Next
    INDEX
    Explanations

    `Alt + F11`

    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
     EditorGUILayout
    1.06
     제거
    1.04
    <unused1183>
    1.03
    <unused1350>
    1.02
    ----+---->
    1.01
    <unused1264>
    1.00
     tighter
    1.00
    |.|.|
    0.99
     APPENDIX
    0.99
     □
    0.99
    POSITIVE LOGITS
    untuk
    0.73
    for
    0.71
    ’
    0.70
    of
    0.69
    '
    0.68
    N
    0.68
     упомина
    0.68
    ↵↵
    0.66
    2
    0.66
    1
    0.64
    Activations Density 0.562%

    No Known Activations