© 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-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 7860
    Prev
    Next
    INDEX
    Explanations

    motivation and determination

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_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
    angkutan
    1.74
    鬻
    1.61
     alien
    1.54
     adjacency
    1.52
     acquaint
    1.51
    ới
    1.50
     acquainted
    1.50
    ijk
    1.50
    IRD
    1.48
     antisymmetric
    1.47
    POSITIVE LOGITS
    💪
    2.20
    励
    2.03
     Quotes
    1.96
     soutenir
    1.94
     Quote
    1.90
     💪
    1.87
    boost
    1.85
    Quote
    1.83
    Stabil
    1.83
    spirational
    1.82
    Activations Density 0.093%

    No Known Activations