© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 8271
    Prev
    Next
    INDEX
    Explanations

    avoiding jargon

    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
    Negative Logits
     Geißler
    1.61
    <unused747>
    1.57
    <unused1728>
    1.49
     konzerv
    1.43
    IContainer
    1.41
    kolah
    1.41
    <unused2134>
    1.40
    锺
    1.38
    λογία
    1.38
    <unused1695>
    1.38
    POSITIVE LOGITS
     etc
    2.06
     which
    1.93
     wonderful
    1.84
     excellent
    1.81
     nice
    1.75
     suggested
    1.73
     another
    1.67
     some
    1.66
     suggestion
    1.66
     qui
    1.66
    Activations Density 0.054%

    No Known Activations