© 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. 10955
    Prev
    Next
    INDEX
    Explanations

    closing markup tags

    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
    ی
    3.27
    ৩০
    3.02
     naturale
    3.01
    ২৬
    2.88
    ordinaire
    2.86
    முதல்
    2.83
    𝙮
    2.80
    ीण
    2.74
    ২৫
    2.71
    userdetails
    2.66
    POSITIVE LOGITS
    ลง
    2.34
    di
    2.19
    /***/
    2.04
    casts
    2.03
    дем
    2.00
    썹
    1.99
    ly
    1.98
     نیچے
    1.95
    sty
    1.94
     spol
    1.93
    Activations Density 0.052%

    No Known Activations