© 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. 14861
    Prev
    Next
    INDEX
    Explanations

    windows api

    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
    ᐉ
    2.82
    ⴹ
    2.76
    Throw
    2.71
    макраты
    2.68
    ವಹ
    2.68
    iale
    2.67
     Gora
    2.66
    Cha
    2.66
     munc
    2.66
     конца
    2.64
    POSITIVE LOGITS
    y
    2.80
    ﻌ
    2.63
    ع
    2.50
    gave
    2.50
    b
    2.48
    i
    2.39
    u
    2.33
    त्सा
    2.32
    kannya
    2.27
    ی
    2.25
    Activations Density 0.003%

    No Known Activations