© 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. 8002
    Prev
    Next
    INDEX
    Explanations

    Gall, Barcel, catal; Gallium, Galactic, Catalanes

    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
    gies
    2.08
    ceme
    1.90
    巧
    1.90
    жере
    1.90
    CDATA
    1.89
    ächs
    1.84
    ل
    1.81
    maz
    1.80
     momentary
    1.80
    mtable
    1.80
    POSITIVE LOGITS
    ócz
    1.51
    Virgin
    1.51
    ניין
    1.51
    ecido
    1.50
     Vou
    1.50
     Virgin
    1.48
    смотре
    1.46
    린
    1.46
    rived
    1.43
    UED
    1.38
    Activations Density 0.186%

    No Known Activations