© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 7284
    Prev
    Next
    INDEX
    Explanations

    qu...ants

    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_13_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
    ꗠ
    1.85
     strListName
    1.71
     "{!}
    1.70
    ꗥ
    1.69
     bilgil
    1.69
     urządzenia
    1.68
     kwal
    1.67
    
    1.67
    
    1.66
    vaegir
    1.65
    POSITIVE LOGITS
    where
    1.06
    ient
    1.05
    by
    0.96
     pairwise
    0.93
     opposite
    0.92
    ly
    0.91
    ↵
    0.87
    0.85
     where
    0.85
    nt
    0.84
    Activations Density 0.020%

    No Known Activations