© 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. 41-GEMMASCOPE-2-RES-65K
    7. 15507
    Prev
    Next
    INDEX
    Explanations

    to

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_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
    -
    0.90
    ‐
    0.81
    ‑
    0.80
    ·
    0.71
    -​
    0.70
    -/
    0.70
    
    0.68
    −
    0.66
    -'
    0.64
    ﹣
    0.63
    POSITIVE LOGITS
    toe
    0.69
    гато
    0.66
    collisions
    0.61
     トー
    0.61
     کمپنیوں
    0.59
     toe
    0.59
     الند
    0.59
    cyj
    0.58
     करण्यास
    0.58
    ブレーキ
    0.57
    Activations Density 0.020%

    No Known Activations