© 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
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 902
    Prev
    Next
    INDEX
    Explanations

    kids and children

    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
     באתר
    1.77
    饵
    1.76
     στη
    1.72
    Insertion
    1.72
     Χ
    1.67
    Μ
    1.66
    Indoor
    1.63
    Κ
    1.63
     με
    1.63
    Sheet
    1.63
    POSITIVE LOGITS
     tyrann
    2.01
     horrend
    1.90
     crude
    1.88
    挈
    1.81
     brutal
    1.76
     tyrannical
    1.76
     dignified
    1.73
     belliger
    1.72
    跚
    1.68
     thinly
    1.68
    Activations Density 0.163%

    No Known Activations