© 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. 2220
    Prev
    Next
    INDEX
    Explanations

    partial positive

    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
    OrCallback
    2.42
    婼
    2.29
    ค์
    2.27
    нё
    2.22
     często
    2.22
    unoscut
    2.17
    ResumeLayout
    2.14
    ी
    2.13
    сум
    2.11
    ാരി
    2.10
    POSITIVE LOGITS
    ons
    1.98
    vio
    1.81
    on
    1.77
     prod
    1.76
    om
    1.75
    ema
    1.74
    ails
    1.62
     ho
    1.61
     prop
    1.61
    ib
    1.59
    Activations Density 0.197%

    No Known Activations