© 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. 773
    Prev
    Next
    INDEX
    Explanations

    creative wordings

    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
    劏
    1.30
    зра
    1.21
     ganglion
    1.20
     Michelin
    1.13
     braz
    1.12
    جار
    1.11
     dada
    1.10
    眯
    1.10
     BAFTA
    1.09
    팟
    1.07
    POSITIVE LOGITS
     freshmen
    1.60
     libero
    1.52
     freshman
    1.47
     varsity
    1.46
    athletics
    1.46
     SUNY
    1.45
     FBS
    1.41
    Academic
    1.40
     academically
    1.39
     Academic
    1.39
    Activations Density 1.048%

    No Known Activations