© 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. 8541
    Prev
    Next
    INDEX
    Explanations

    engage with audience

    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
    adolu
    1.71
    enance
    1.44
     Gild
    1.43
    zentration
    1.42
    ранже
    1.41
    kve
    1.38
     ?>">
    1.37
    克兰
    1.37
     vzdu
    1.36
    ühle
    1.36
    POSITIVE LOGITS
     dormir
    2.11
    contrar
    2.03
    ulators
    1.99
     usc
    1.98
    ัญลักษณ์
    1.91
     indire
    1.88
    وضع
    1.87
    ianos
    1.82
    head
    1.82
     dàng
    1.82
    Activations Density 0.198%

    No Known Activations