© 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. 519
    Prev
    Next
    INDEX
    Explanations

    make sure, make better, made from

    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
    Qnt
    1.20
    Genres
    1.20
    遥
    1.19
    什么时候
    1.11
    Quieres
    1.09
    antically
    1.08
    嚀
    1.08
     sebepler
    1.07
     ratione
    1.07
    앵
    1.06
    POSITIVE LOGITS
     inroads
    2.51
     sure
    2.39
     amends
    2.23
     sense
    2.21
    leine
    2.18
     headway
    2.07
     landfall
    1.87
     aware
    1.85
     use
    1.82
     mistake
    1.82
    Activations Density 1.415%

    No Known Activations