© 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. 7101
    Prev
    Next
    INDEX
    Explanations

    harmless AI assistant

    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
    chung
    1.82
    ','$
    1.68
     **/
    1.63
    ung
    1.62
    め
    1.61
    치는
    1.60
     '*.
    1.59
    ",&
    1.59
    
    1.58
    oreg
    1.58
    POSITIVE LOGITS
    多久
    0.95
     PayPay
    0.82
     depth
    0.78
     breath
    0.75
     Vázquez
    0.72
     gradio
    0.72
     tepat
    0.70
     exhale
    0.70
    当我
    0.68
     minutes
    0.67
    Activations Density 0.025%

    No Known Activations