© 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. 22-GEMMASCOPE-2-RES-16K
    7. 9934
    Prev
    Next
    INDEX
    Explanations

    code syntax for objects and functions

    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_22_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
     EditorGUILayout
    0.96
    đe
    0.92
    вори
    0.91
    triangleq
    0.90
     jumped
    0.88
    ativos
    0.88
    արգ
    0.86
    //=
    0.86
    irik
    0.85
    orduk
    0.84
    POSITIVE LOGITS
     true
    1.14
    true
    1.07
     TEN
    0.94
     []);
    0.93
     false
    0.93
    ５
    0.91
    5
    0.89
     II
    0.89
     Wood
    0.89
     Lang
    0.89
    Activations Density 0.045%

    No Known Activations