© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 56
    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_22_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
    äft
    0.89
    を中心
    0.89
     teníamos
    0.86
     constituyen
    0.85
    ụp
    0.84
    いただき
    0.82
     pente
    0.80
    ẩ
    0.79
     मिळ
    0.79
     सबक
    0.78
    POSITIVE LOGITS
     said
    3.65
    said
    3.23
     says
    3.21
     mengatakan
    3.00
     say
    3.00
     saying
    2.98
    says
    2.85
     stated
    2.82
     Said
    2.62
     Says
    2.61
    Activations Density 4.522%

    No Known Activations