© 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. 8531
    Prev
    Next
    INDEX
    Explanations

    does the

    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
    .
    2.04
    ish
    1.92
    es
    1.88
    is
    1.81
    ...
    1.80
    (
    1.79
    Is
    1.76
     Is
    1.68
     (
    1.65
    '
    1.61
    POSITIVE LOGITS
     становништво
    1.54
    artoum
    1.49
    <unused1728>
    1.48
     wpt
    1.43
    chrane
    1.42
     EnglishChoose
    1.41
     Eldorado
    1.41
     audiovisual
    1.40
     Macedonia
    1.40
    قليم
    1.40
    Activations Density 0.025%

    No Known Activations