© 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. 7-GEMMASCOPE-2-RES-16K
    7. 12674
    Prev
    Next
    INDEX
    Explanations

    MATLAB and mathematical expressions

    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_7_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
    窕
    2.78
    EditorGUI
    2.73
    രിക്കും
    2.66
    incinn
    2.59
    ྒྱ
    2.58
    र्वाद
    2.51
    сть
    2.49
    র্জা
    2.43
    CameraController
    2.40
    commod
    2.36
    POSITIVE LOGITS
    satz
    2.41
    あって
    2.03
    ي
    2.00
    {'
    1.95
     realised
    1.88
     realized
    1.80
    ตุ
    1.77
    яў
    1.70
    <0xBE>
    1.69
     went
    1.66
    Activations Density 0.057%

    No Known Activations