© 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. 4007
    Prev
    Next
    INDEX
    Explanations

    Easier, Bathed, Scattering

    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
    řad
    1.44
     Shimano
    1.35
     centrales
    1.35
    烯
    1.30
    LaTeX
    1.26
    粕
    1.25
     ActiveRecord
    1.24
    arkt
    1.24
    inizin
    1.21
    insen
    1.21
    POSITIVE LOGITS
    coming
    1.99
    naments
    1.98
    eworthy
    1.94
    льных
    1.92
    ﹰ
    1.91
    withstanding
    1.90
    whelming
    1.87
     tine
    1.86
    liness
    1.85
    льными
    1.85
    Activations Density 0.687%

    No Known Activations