© 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. 3301
    Prev
    Next
    INDEX
    Explanations

    specifying units of time or quantity

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Prejudice
    1.01
    ⒉
    1.00
    ₂
    0.99
    ٢
    0.96
    
    0.95
    ２
    0.95
    ₂)
    0.95
     overwritten
    0.90
    ²
    0.90
     Dementia
    0.89
    POSITIVE LOGITS
     Greeley
    1.79
     revenue
    1.64
     nont
    1.63
     revenues
    1.55
    gehen
    1.53
     Juárez
    1.51
     Durango
    1.50
    йо
    1.50
     shooter
    1.49
     Yankee
    1.49
    Activations Density 0.031%

    No Known Activations