© 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. 223
    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
    Reply
    0.53
    Title
    0.52
    http
    0.51
    ©
    0.49
    Link
    0.48
    youtu
    0.46
    Command
    0.45
    Donate
    0.45
    Early
    0.45
    ่
    0.44
    POSITIVE LOGITS
     गिवन
    0.79
     ziemlich
    0.68
    <unused2130>
    0.66
    <unused89>
    0.65
    ější
    0.63
     zahlreichen
    0.62
    <unused1036>
    0.62
    <unused1721>
    0.62
     çeşitli
    0.61
     verschillende
    0.61
    Activations Density 4.507%

    No Known Activations