Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 4003
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
    y
    2.27
    elda
    2.20
    yó
    2.03
    يقة
    2.01
    yng
    1.97
    ghed
    1.96
    人用
    1.88
    edian
    1.86
    estrutura
    1.84
    פתח
    1.82
    POSITIVE LOGITS
     servos
    2.30
     compass
    2.06
    বিধি
    2.05
     governed
    2.04
    러
    1.99
    ិត
    1.95
    굴
    1.95
    ს
    1.94
     Pics
    1.93
    havior
    1.89
    Activations Density 0.505%

    No Known Activations