© 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. 2929
    Prev
    Next
    INDEX
    Explanations

    system's components and attributes

    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
    -
    1.71
    /
    1.63
    ing
    1.50
    '
    1.48
    ds
    1.41
    ed
    1.39
    by
    1.38
    =
    1.36
    1
    1.35
    as
    1.34
    POSITIVE LOGITS
     revamped
    2.63
     coffers
    2.57
     flagship
    2.50
     mascot
    2.35
     infamous
    2.34
     dracon
    2.34
    irteenth
    2.33
     Largest
    2.31
     }}(
    2.29
     steepest
    2.28
    Activations Density 0.446%

    No Known Activations