© 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. 8374
    Prev
    Next
    INDEX
    Explanations

    started reading

    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
     an
    0.74
    0.70
     a
    0.63
    an
    0.63
    adir
    0.63
     “
    0.61
    idän
    0.61
     "
    0.58
    <em>
    0.58
     $
    0.56
    POSITIVE LOGITS
     ويت
    2.12
     знает
    2.08
    والفق
    2.00
     depende
    1.99
     исполнения
    1.98
    会不会
    1.98
     والأ
    1.98
     يسم
    1.97
    禿
    1.97
     наві
    1.97
    Activations Density 0.004%

    No Known Activations