© 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. 7801
    Prev
    Next
    INDEX
    Explanations

    protecting and saving

    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
    actual
    2.26
     ACTUAL
    2.21
    incy
    2.15
    画像の
    2.14
    arty
    2.09
    ucion
    2.09
    áis
    2.08
    \}$.
    2.07
    íguez
    2.07
    uyendo
    2.06
    POSITIVE LOGITS
     ahead
    1.86
     etern
    1.60
     изд
    1.48
     ruth
    1.37
     forever
    1.36
     imper
    1.31
     away
    1.30
     empires
    1.29
     bohater
    1.28
     maneiras
    1.27
    Activations Density 0.022%

    No Known Activations