© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 11407
    Prev
    Next
    INDEX
    Explanations

    just following

    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
     of
    2.02
    of
    1.90
    cl
    1.63
    all
    1.51
     ofthe
    1.50
     AND
    1.49
     و
    1.48
     Of
    1.46
    at
    1.46
    and
    1.44
    POSITIVE LOGITS
     générateur
    1.83
     ética
    1.75
     nécessité
    1.75
     mengingat
    1.74
     densément
    1.73
    Cuánto
    1.71
     každ
    1.69
     réserv
    1.69
     sofá
    1.67
     această
    1.66
    Activations Density 0.003%

    No Known Activations