© 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
    2. Gemma-3-1B
    3. 22-GEMMASCOPE-2-RES-16K
    4. 571
    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
     frecuente
    0.89
     gyak
    0.88
     ritrov
    0.87
     dreaded
    0.84
     constate
    0.81
    ERATE
    0.81
     sering
    0.79
    묘
    0.78
    бычно
    0.78
     considerazione
    0.78
    POSITIVE LOGITS
     designed
    1.96
    designed
    1.77
     Designed
    1.56
    Designed
    1.56
     aimed
    1.51
     crafted
    1.49
     geared
    1.48
     outfitted
    1.42
     intended
    1.37
     tailored
    1.36
    Activations Density 2.436%

    No Known Activations