© 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. 12196
    Prev
    Next
    INDEX
    Explanations

    LaTeX geometry configuration

    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
    wc
    2.63
    w
    2.52
    cia
    2.52
    qiya
    2.45
    ss
    2.31
    rol
    2.30
    ्रेडिट
    2.29
    lor
    2.25
    la
    2.25
    ipasi
    2.20
    POSITIVE LOGITS
    AWSJavaScriptSDK
    3.01
     cuad
    2.95
    े
    2.86
    המ
    2.85
     satisfe
    2.75
    ു
    2.70
    econ
    2.68
     doce
    2.68
     bricks
    2.67
     нака
    2.65
    Activations Density 0.002%

    No Known Activations