© 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. 13921
    Prev
    Next
    INDEX
    Explanations

    authoritarian regimes and rule

    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
     Unexpected
    2.28
    hava
    2.24
    Unexpected
    2.22
    ו
    2.19
    ۣ
    2.19
    hame
    2.18
    y
    2.16
     unexpected
    2.15
    h
    2.14
    ல்லாம்
    2.09
    POSITIVE LOGITS
    ائق
    1.86
    داً
    1.84
    ovol
    1.83
    섭
    1.75
    iec
    1.73
     নির্বাহী
    1.72
    اتھ
    1.71
    ną
    1.69
    ྫ
    1.67
    amt
    1.66
    Activations Density 0.013%

    No Known Activations