© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 1516
    Prev
    Next
    INDEX
    Explanations

    categories and classifications

    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
    ulkner
    1.62
    必备
    1.51
    itty
    1.48
     cauza
    1.43
    чески
    1.42
    頃
    1.42
    uscany
    1.42
    ่อม
    1.41
    ارى
    1.41
    errorhandler
    1.40
    POSITIVE LOGITS
     보도록
    1.30
    凸
    1.28
     놓고
    1.27
    oil
    1.21
    يج
    1.18
    落在
    1.13
     ALJ
    1.12
    dui
    1.12
    Oil
    1.11
     portée
    1.11
    Activations Density 0.048%

    No Known Activations