© 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. 3883
    Prev
    Next
    INDEX
    Explanations

    What is

    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
    ərə
    1.86
     appréci
    1.84
    ılı
    1.80
    ="'
    1.76
    ικη
    1.76
    扞
    1.74
     anthe
    1.74
    startDate
    1.72
    ƣ
    1.72
    ahmatullahi
    1.71
    POSITIVE LOGITS
    dumps
    1.29
    忽然
    1.26
    何の
    1.20
    想到
    1.17
    突然
    1.16
     Suddenly
    1.14
    眼鏡
    1.11
     fuck
    1.10
     yere
    1.09
    到现在
    1.07
    Activations Density 0.144%

    No Known Activations