© 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. 1971
    Prev
    Next
    INDEX
    Explanations

    images and quotes

    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
     hade
    1.56
     upp
    1.56
     personalizados
    1.53
     sarees
    1.52
    কার
    1.52
     웨
    1.50
    ો
    1.48
     ondas
    1.48
     ultrasonic
    1.47
    鑼
    1.45
    POSITIVE LOGITS
    Mine
    1.61
    Critics
    1.57
    Collaboration
    1.51
    Liberal
    1.49
    Critic
    1.45
    debate
    1.44
    Politics
    1.43
    Acting
    1.39
    Qualifier
    1.38
    mining
    1.38
    Activations Density 0.151%

    No Known Activations