© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 2656
    Prev
    Next
    INDEX
    Explanations

    like a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_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
     cárc
    2.23
     enl
    2.18
    槸
    2.06
    FlaskApp
    2.00
    ขัน
    1.93
    AuthState
    1.90
    ssh
    1.88
    
    1.86
    runner
    1.86
     servidores
    1.85
    POSITIVE LOGITS
    eneg
    2.03
    այն
    1.86
     کنس
    1.86
    হেতু
    1.83
    javax
    1.75
     formular
    1.74
    rayon
    1.73
    enen
    1.73
    деся
    1.72
    TOOLS
    1.72
    Activations Density 0.174%

    No Known Activations