© 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. 3302
    Prev
    Next
    INDEX
    Explanations

    productivity

    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
    ’
    1.29
    நாயக
    1.20
    ‘
    1.11
     conte
    1.10
    Give
    1.07
    AB
    1.06
    твер
    1.06
     Promise
    1.06
    We
    1.03
    THE
    1.02
    POSITIVE LOGITS
     earthen
    1.24
    罾
    1.07
    ccgi
    1.06
    nå
    1.06
    fledged
    1.04
    𝙧
    1.04
     precipitation
    1.04
    basin
    1.04
    া
    1.04
    iarism
    1.03
    Activations Density 0.002%

    No Known Activations