© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 6216
    Prev
    Next
    INDEX
    Explanations

    file path operations

    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_12_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
     kaikki
    1.28
     gesamten
    1.21
     varje
    1.20
    全ての
    1.20
    每一個
    1.17
     setiap
    1.14
     svaki
    1.10
     =[
    1.05
    rijving
    1.04
     éves
    1.03
    POSITIVE LOGITS
     shenanigans
    2.71
     spicy
    2.59
     fruity
    2.49
     twists
    2.47
     naughty
    2.47
     splurge
    2.46
     sneaky
    2.43
     sexy
    2.41
     adventurous
    2.41
     fancy
    2.41
    Activations Density 0.307%

    No Known Activations