© 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. 15-GEMMASCOPE-2-RES-16K
    7. 6198
    Prev
    Next
    INDEX
    Explanations

    can afford or realistically achieve

    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
     mêmes
    1.05
     magnifique
    1.00
    bien
    0.99
    Kit
    0.99
    Teri
    0.96
    曆
    0.93
     refreshed
    0.93
    чатку
    0.93
    c
    0.92
    kor
    0.92
    POSITIVE LOGITS
     tolerate
    2.42
     prioritise
    2.34
     find
    2.33
     prioritize
    2.29
     muster
    2.28
     abide
    2.27
     consume
    2.23
     poke
    2.22
     degrade
    2.20
     devote
    2.18
    Activations Density 0.050%

    No Known Activations