© 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. 6959
    Prev
    Next
    INDEX
    Explanations

    cannot provide information or assistance

    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
    btnLogin
    1.80
    逝
    1.68
    popupButton
    1.68
    setWindowTitle
    1.67
    btnPrint
    1.67
     cherche
    1.63
    顫
    1.62
     atribu
    1.61
    férence
    1.56
    ButtonClick
    1.55
    POSITIVE LOGITS
     intrat
    2.13
    wikimedia
    1.95
    Ꭿ
    1.94
    ΐ
    1.89
    dail
    1.89
    svg
    1.88
     anon
    1.85
    lains
    1.84
    σότε
    1.80
     instrumental
    1.79
    Activations Density 0.114%

    No Known Activations