© 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. 359
    Prev
    Next
    INDEX
    Explanations

    "in" followed by common words

    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
    ます
    0.75
    llo
    0.72
    ки
    0.71
    tan
    0.71
    y
    0.69
    تام
    0.68
    न
    0.68
    ますが
    0.67
    lc
    0.66
    تبر
    0.65
    POSITIVE LOGITS
    \"
    0.57
    もちろん
    0.56
    $:
    0.54
    Η
    0.54
    值
    0.54
    \#
    0.53
    ﺎ
    0.52
    ﻨ
    0.52
     ένας
    0.51
    үүн
    0.51
    Activations Density 0.801%

    No Known Activations