© 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. 12-GEMMASCOPE-2-RES-16K
    7. 5278
    Prev
    Next
    INDEX
    Explanations

    continue and WriteLine

    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
    tml
    1.27
    plica
    1.25
     السب
    1.24
     Comanche
    1.20
     السوق
    1.18
    ^{*}+
    1.18
    adio
    1.18
    pozy
    1.18
    pra
    1.16
    uncan
    1.16
    POSITIVE LOGITS
     detainees
    1.35
     inmate
    1.33
     Oversight
    1.32
     embezz
    1.32
    溯
    1.31
     overseen
    1.29
     lockdowns
    1.29
     strict
    1.29
     briefing
    1.28
     prison
    1.28
    Activations Density 0.000%

    No Known Activations