© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 2673
    Prev
    Next
    INDEX
    Explanations

    co- words beginning

    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_15_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
    catching
    1.66
    っぱい
    1.45
     majoring
    1.30
    chiha
    1.30
    tain
    1.30
     catching
    1.29
    켠
    1.29
    讳
    1.27
    葺
    1.26
    oubt
    1.24
    POSITIVE LOGITS
    ordinated
    1.90
    ordinating
    1.82
    astal
    1.79
    orden
    1.75
    ordinates
    1.68
    imbatore
    1.65
    chrane
    1.64
     ord
    1.62
    arser
    1.62
    ordination
    1.61
    Activations Density 0.056%

    No Known Activations