© 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. 6937
    Prev
    Next
    INDEX
    Explanations

    programming languages and paradigms

    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
    obucket
    1.46
    橿
    1.37
    ifts
    1.33
    ifting
    1.33
    ⵏ
    1.33
    WORTH
    1.32
     jata
    1.32
    颊
    1.31
    廓
    1.29
     množ
    1.27
    POSITIVE LOGITS
    matically
    3.37
    atically
    2.88
    schluss
    2.86
    mers
    2.81
    miers
    2.80
    mazione
    2.78
    MING
    2.78
    matical
    2.71
     progr
    2.59
    DEFG
    2.59
    Activations Density 0.056%

    No Known Activations