© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 3608
    Prev
    Next
    INDEX
    Explanations

    URLs ending in .com

    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
     也
    4.42
     餐
    3.83
     除了
    3.67
     會
    3.66
     以及
    3.65
     文件
    3.61
     因此
    3.61
     抗
    3.58
     其他
    3.58
     然而
    3.57
    POSITIVE LOGITS
    য়ো
    2.84
    ään
    2.72
    agregar
    2.60
    মাণের
    2.55
    os
    2.53
    field
    2.38
    Fra
    2.34
    tanto
    2.33
    Ã
    2.30
    ografia
    2.29
    Activations Density 0.020%

    No Known Activations