© 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. 6750
    Prev
    Next
    INDEX
    Explanations

    can be

    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
    禾
    1.93
     distin
    1.81
    瓊
    1.80
     Stopping
    1.74
    羸
    1.71
     distingue
    1.70
     stoppage
    1.68
     exemple
    1.68
     destacar
    1.66
    pection
    1.66
    POSITIVE LOGITS
     refrigerant
    0.90
     tartalmaz
    0.80
     dermat
    0.78
    |-
    0.76
    luğ
    0.74
     erw
    0.73
    arial
    0.71
    rang
    0.70
    translate
    0.69
     dioxane
    0.68
    Activations Density 0.016%

    No Known Activations