© 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. 3527
    Prev
    Next
    INDEX
    Explanations

    closing punctuation or quotes

    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
     FCM
    0.93
     Spo
    0.89
     spl
    0.81
    ゎ
    0.78
    sca
    0.77
    msk
    0.75
     poop
    0.72
     cht
    0.70
    isé
    0.70
     danced
    0.70
    POSITIVE LOGITS
    Accelerator
    1.63
     ventilators
    1.42
    Citation
    1.39
    奨
    1.39
    Identifier
    1.39
    Henderson
    1.38
     ventilator
    1.37
     accelerator
    1.36
     evaluator
    1.35
    ellent
    1.35
    Activations Density 0.088%

    No Known Activations