© 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. 7941
    Prev
    Next
    INDEX
    Explanations

    writing code, suggestions, explanations

    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
    RELATED
    1.90
    ործ
    1.58
     said
    1.58
    OBJECT
    1.54
    ūk
    1.53
    澍
    1.51
    aan
    1.50
     CLICK
    1.50
     discerned
    1.50
    GROUND
    1.50
    POSITIVE LOGITS
    ://
    1.77
    кты
    1.71
    omnia
    1.70
     Moreton
    1.64
    imore
    1.63
     version
    1.63
     wheelbase
    1.61
     versie
    1.60
     edn
    1.60
    aughton
    1.60
    Activations Density 0.019%

    No Known Activations