© 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. 15-GEMMASCOPE-2-RES-16K
    7. 2562
    Prev
    Next
    INDEX
    Explanations

    error messages and code blocks

    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
     fett
    1.47
    спомина
    1.42
     martial
    1.39
    BOUND
    1.38
    Dragon
    1.35
    pian
    1.35
     桌
    1.35
     buch
    1.34
    унд
    1.34
     сравнению
    1.33
    POSITIVE LOGITS
     ===
    1.19
    !==
    1.13
     !==
    1.10
    énie
    1.07
    URIComponent
    1.02
    ishna
    1.01
    ñez
    0.99
    ése
    0.95
    maar
    0.93
     genoemd
    0.93
    Activations Density 0.002%

    No Known Activations