© 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. 9526
    Prev
    Next
    INDEX
    Explanations

    bash script start

    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
    ↵↵
    1.43
    ଡ
    1.14
    ⤷
    1.06
    ം
    1.03
    ಕಾಶ
    0.97
    ട്ട
    0.96
    melt
    0.94
    ============
    0.92
    ли
    0.91
    ppu
    0.89
    POSITIVE LOGITS
    <blockquote>
    1.63
    ↵
    1.31
     {@
    1.30
    /***/
    1.19
     pins
    1.19
    transferases
    1.09
    REETYPE
    1.08
    ப்பட்டு
    1.08
    娌
    1.07
     lack
    1.06
    Activations Density 0.012%

    No Known Activations