© 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. 17-GEMMASCOPE-2-RES-16K
    7. 92
    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_17_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
    lef
    0.53
    <0xC2>
    0.53
    odd
    0.50
    лла
    0.50
    ???
    0.49
    ooo
    0.49
    ・・・
    0.49
    Ic
    0.49
    yce
    0.49
    ....
    0.48
    POSITIVE LOGITS
     früheren
    0.65
     pandémie
    0.60
     veículo
    0.60
     größeren
    0.59
     собой
    0.58
     년
    0.57
     기업
    0.57
     rynku
    0.57
     höhere
    0.55
     pressão
    0.55
    Activations Density 7.103%

    No Known Activations