© 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-3-12B
    5. 12-GEMMASCOPE-2-RES-16K
    7. 104
    Prev
    Next
    INDEX
    Explanations

    in + following word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_12_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
    ம்
    1.86
    س
    1.58
    >
    1.51
    in
    1.32
    j
    1.30
    viet
    1.29
    1
    1.29
    ہ
    1.26
    t
    1.25
    ων
    1.22
    POSITIVE LOGITS
     وفي
    2.08
    ا
    1.95
     وبين
    1.88
    ı
    1.64
    ılarak
    1.52
    부터
    1.50
     kojem
    1.45
    外的
    1.44
    客様
    1.40
    ü
    1.35
    Activations Density 1.557%

    No Known Activations