© 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. 1411
    Prev
    Next
    INDEX
    Explanations

    Hi followed by query

    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
     Ін
    2.16
     Αν
    2.15
     Раз
    2.07
     Ο
    2.00
     Λ
    1.97
     Πα
    1.96
     Β
    1.92
     Пу
    1.90
     Επι
    1.89
     Київ
    1.87
    POSITIVE LOGITS
    nie
    1.80
    uwe
    1.71
    nya
    1.66
    nies
    1.64
    ny
    1.54
    nen
    1.53
    nal
    1.52
    riele
    1.49
    ly
    1.47
    ders
    1.46
    Activations Density 0.270%

    No Known Activations