© 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. 1514
    Prev
    Next
    INDEX
    Explanations

    I understand

    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
     thờ
    1.52
     mapp
    1.50
     khấu
    1.50
    ndown
    1.46
     ######
    1.45
     Dern
    1.45
    ikaner
    1.44
     Kimberley
    1.42
    臃
    1.41
    したいと思います
    1.41
    POSITIVE LOGITS
     그러니까
    0.95
    这句话
    0.88
    ־
    0.81
    context
    0.81
    repent
    0.77
    这话
    0.77
     meningitis
    0.76
     cardiomyocyte
    0.74
    itación
    0.73
     semantics
    0.73
    Activations Density 0.335%

    No Known Activations