© 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. 10492
    Prev
    Next
    INDEX
    Explanations

    slash, command separator

    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
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    2.83
    یت
    2.73
    Highly
    2.58
    ⿱
    2.55
    ייה
    2.42
    ামুটি
    2.38
    ियमित
    2.26
    γμα
    2.25
     Highly
    2.23
    ⿷
    2.20
    POSITIVE LOGITS
    cry
    2.87
    dery
    2.87
    roix
    2.86
    
    2.82
     groves
    2.81
    
    2.80
    त्रेयी
    2.77
    
    2.73
    
    2.67
     elastomers
    2.64
    Activations Density 0.001%

    No Known Activations