© 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. 13-GEMMASCOPE-2-RES-65K
    7. 448
    Prev
    Next
    INDEX
    Explanations

    handstand emoji

    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_13_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
    and
    0.59
    –
    0.58
    -
    0.55
    скую
    0.49
    certain
    0.49
    하지만
    0.48
    رير
    0.48
     …
    0.47
    ẫu
    0.46
    与其
    0.46
    POSITIVE LOGITS
     majestic
    0.93
     sorrow
    0.92
     wondrous
    0.90
     welfare
    0.87
    ઞ
    0.87
     meravigli
    0.87
    支出
    0.86
    न्देल
    0.86
    তীশ
    0.85
     rhythmic
    0.85
    Activations Density 0.006%

    No Known Activations