© 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. 3892
    Prev
    Next
    INDEX
    Explanations

    Gemma team

    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
    ercises
    1.54
    empê
    1.44
    REPEAT
    1.39
     evidences
    1.39
     activism
    1.36
    ༽
    1.36
     pleadings
    1.36
    ECT
    1.33
     Gins
    1.33
     restless
    1.32
    POSITIVE LOGITS
    จาก
    1.30
    經過
    1.16
    有限
    1.14
    จากการ
    1.12
    ที่ไม่
    1.08
     barat
    1.08
     koja
    1.08
    <start_of_image>
    1.07
     mali
    1.06
    에서
    1.06
    Activations Density 0.004%

    No Known Activations