© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 379
    Prev
    Next
    INDEX
    Explanations

    please provide information

    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
     Commonly
    1.28
    Optimal
    1.14
    Selecting
    1.10
     Entering
    1.06
    咫
    1.05
    Selection
    1.03
     inescapable
    1.02
     desiring
    1.02
    Preference
    1.01
     commonplace
    1.01
    POSITIVE LOGITS
     enlighten
    1.51
     wait
    1.48
     tell
    1.46
    ::*;
    1.39
    看一下
    1.36
     congr
    1.36
     watch
    1.35
    ลอง
    1.34
    再说
    1.34
     send
    1.33
    Activations Density 2.622%

    No Known Activations