© 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. 8483
    Prev
    Next
    INDEX
    Explanations

    erotically, erodes, ergonomics

    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
     Quantity
    1.70
    idelity
    1.70
    Judgment
    1.70
     أ
    1.69
    dropdown
    1.69
    阂
    1.68
     plu
    1.67
    setcounter
    1.67
     transf
    1.67
    คับ
    1.65
    POSITIVE LOGITS
    skine
    2.35
     bhavanti
    2.06
    nesto
    2.02
    퓸
    1.91
     bhavati
    1.86
     dhammo
    1.86
    sley
    1.85
    είς
    1.78
    amental
    1.77
    ogenous
    1.74
    Activations Density 0.028%

    No Known Activations