© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 12987
    Prev
    Next
    INDEX
    Explanations

    agreement made as of

    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_13_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    𝒐
    1.94
    ﻟ
    1.87
    此之外
    1.81
    кр
    1.81
    yap
    1.78
     "*.
    1.75
    iya
    1.74
    𝘮
    1.72
    ‰
    1.71
    зре
    1.71
    POSITIVE LOGITS
    ༌
    2.01
    </tr>
    1.98
    しくは
    1.85
     inci
    1.82
     cen
    1.67
    ([]
    1.65
    istin
    1.63
    द
    1.59
    oneg
    1.57
    ist
    1.55
    Activations Density 0.000%

    No Known Activations