© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 3316
    Prev
    Next
    INDEX
    Explanations

    function definitions

    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_15_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
    としている
    1.19
     названием
    1.13
    ármaz
    1.11
     upkeep
    1.09
    laughter
    1.06
     Redeem
    1.05
    どころ
    1.01
    <unused63>
    1.00
     tils
    1.00
    Референце
    1.00
    POSITIVE LOGITS
    eto
    1.20
    esar
    1.15
    etti
    1.15
    נטי
    1.13
    esa
    1.12
    iyan
    1.10
     jut
    1.08
    umat
    1.08
    essen
    1.07
    XY
    1.05
    Activations Density 0.000%

    No Known Activations