© 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. 15-GEMMASCOPE-2-RES-16K
    7. 7165
    Prev
    Next
    INDEX
    Explanations

    to shrink or distort

    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_15_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
     beri
    1.35
    amię
    1.23
     fin
    1.18
    )</
    1.17
     men
    1.17
    issez
    1.14
    > </
    1.14
     respe
    1.13
     male
    1.13
    </
    1.13
    POSITIVE LOGITS
    flipped
    1.49
     contradicted
    1.47
     الواقع
    1.38
     contradicts
    1.35
     actually
    1.34
    bbb
    1.33
     deviates
    1.33
    čkog
    1.32
    actually
    1.32
    fitted
    1.31
    Activations Density 0.035%

    No Known Activations