© 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. 1069
    Prev
    Next
    INDEX
    Explanations

    "others" or "other things"

    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
    .';
    1.08
    ˝
    1.07
    »;
    1.02
    !`
    1.01
    !';
    0.99
    畏
    0.98
    ｣
    0.95
    &#
    0.94
    ,»
    0.93
    」「
    0.93
    POSITIVE LOGITS
     stuff
    2.23
     things
    2.16
     REALLY
    2.11
     really
    2.08
     cosas
    2.06
     THINGS
    1.98
     thing
    1.98
     coisas
    1.98
     someplace
    1.96
     whatnot
    1.96
    Activations Density 1.743%

    No Known Activations