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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 1490
    Prev
    Next
    INDEX
    Explanations

    higher degree

    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
     vostre
    1.90
     Bunny
    1.87
     váš
    1.80
     THAT
    1.78
    mee
    1.75
     playfully
    1.72
    ྵ
    1.70
     realist
    1.70
     vostro
    1.69
     menciptakan
    1.68
    POSITIVE LOGITS
     separations
    1.86
     separation
    1.81
     deterioration
    1.74
     discrepancies
    1.67
     dislocations
    1.66
     disturbances
    1.64
    نف
    1.63
     separación
    1.61
     penurunan
    1.61
    ڱ
    1.60
    Activations Density 0.288%

    No Known Activations