© 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. 6472
    Prev
    Next
    INDEX
    Explanations

    code properties and declarations

    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
     “
    1.17
     Page
    0.95
    <eos>
    0.91
     L
    0.90
    ’
    0.88
     ‘
    0.87
    ↵↵
    0.84
     Part
    0.83
    “
    0.81
    ‘
    0.79
    POSITIVE LOGITS
    okatokat
    2.02
    atthanam
    1.72
     datth
    1.67
    itabbo
    1.63
    apetva
    1.63
    atthane
    1.62
     SIINFE
    1.61
    akkhati
    1.60
     saddas
    1.60
     ortam
    1.59
    Activations Density 0.007%

    No Known Activations