© 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. 2903
    Prev
    Next
    INDEX
    Explanations

    combined words and phrases

    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
     Pública
    1.51
     Committee
    1.40
     Guide
    1.36
     Militia
    1.34
     Pressed
    1.29
     pubblico
    1.27
     Duty
    1.25
     ƒ
    1.23
     Obed
    1.23
     Debate
    1.23
    POSITIVE LOGITS
    uvi
    1.66
    otri
    1.64
    ettings
    1.62
    ustainability
    1.61
    attham
    1.60
    thai
    1.59
    cellaneous
    1.58
    avian
    1.58
    astri
    1.57
    aii
    1.56
    Activations Density 11.266%

    No Known Activations