© 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
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-65K
    4. 2701
    Prev
    Next
    INDEX
    Explanations

    action verbs followed by descriptions

    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
    ผม
    0.96
     ног
    0.94
     B
    0.93
    คน
    0.93
    นิด
    0.92
    ชาว
    0.90
     myself
    0.90
     I
    0.90
    他人
    0.90
     passions
    0.89
    POSITIVE LOGITS
     தெரிவித்துள்ளது
    1.81
     자체
    1.81
     ತನ್ನ
    1.70
     menyediakan
    1.69
     சார்பில்
    1.69
     Announces
    1.68
    旗下
    1.66
     itself
    1.65
    irikan
    1.60
     공식
    1.55
    Activations Density 1.536%

    No Known Activations