© 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. 415
    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
    ро
    0.40
    ro
    0.39
    <unused61>
    0.38
    -
    0.37
     thế
    0.37
    out
    0.37
    <unused63>
    0.37
     out
    0.37
    i
    0.36
    ika
    0.35
    POSITIVE LOGITS
    MARK
    0.58
    Mees
    0.53
    ELER
    0.52
     Kxf
    0.52
    𠃊
    0.52
    <unused892>
    0.52
     Bên
    0.51
    徥
    0.51
    स्यों
    0.51
    ാരി
    0.51
    Activations Density 2.607%

    No Known Activations