© 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. 877
    Prev
    Next
    INDEX
    Explanations

    by choosing

    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
    ా
    3.03
    ielt
    2.88
    elez
    2.83
    ार्मिक
    2.76
    alai
    2.70
    orca
    2.66
    ጥነት
    2.65
    ة
    2.63
    係る
    2.61
    وفر
    2.58
    POSITIVE LOGITS
    ته
    3.72
    تی
    3.10
    zantine
    2.68
     virtue
    2.63
    zant
    2.63
    tyn
    2.58
    rimidine
    2.54
    ნ
    2.54
    헉
    2.54
     dil
    2.47
    Activations Density 0.824%

    No Known Activations