© 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. 13-GEMMASCOPE-2-RES-16K
    7. 14952
    Prev
    Next
    INDEX
    Explanations

    zero trust, nth largest

    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
    Not in Any Lists

    No Comments

    Negative Logits
    უნ
    1.12
    ̈
    1.10
    ritz
    1.08
    ᅴ
    1.06
    rza
    1.06
    <0x8C>
    1.04
    ても
    1.04
    glTranslatef
    1.03
    awak
    1.03
    yers
    1.02
    POSITIVE LOGITS
     quantités
    1.37
     médio
    1.24
     organisé
    1.23
     quantité
    1.22
     linéaire
    1.21
     değeri
    1.19
    
    1.17
    Qty
    1.16
     الصحي
    1.16
     tồn
    1.16
    Activations Density 0.013%

    No Known Activations