© 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-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 1293
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_17_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     quite
    0.72
    <b>
    0.72
     **
    0.71
    …
    0.65
     >>
    0.60
     *
    0.59
    **
    0.59
    >>
    0.59
    delta
    0.58
    टेगरी
    0.56
    POSITIVE LOGITS
    㫣
    1.08
    㳯
    0.98
    㿟
    0.98
    䛛
    0.97
     pertain
    0.96
     désigne
    0.96
    龵
    0.95
    籿
    0.95
     মধ্যকার
    0.94
    <unused1715>
    0.94
    Activations Density 2.935%

    No Known Activations