© 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. 7073
    Prev
    Next
    INDEX
    Explanations

    lists of data or conditions

    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
     so
    1.72
    “…
    1.69
    Coral
    1.52
     lily
    1.52
     very
    1.50
     „
    1.47
    ❝
    1.46
     sooo
    1.46
     mine
    1.45
     scarlet
    1.43
    POSITIVE LOGITS
    ローラー
    1.52
    asaan
    1.52
    푼
    1.50
     осіб
    1.45
    anyo
    1.38
    bolts
    1.37
    aisa
    1.36
    ataa
    1.35
    attham
    1.34
     runApp
    1.33
    Activations Density 0.004%

    No Known Activations