© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 592
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-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
     extrapol
    0.82
     neuron
    0.78
     massless
    0.77
     =
    0.74
     extrapolation
    0.72
     extrapolated
    0.72
     deuter
    0.70
     infinite
    0.69
     isotropic
    0.69
     polinom
    0.69
    POSITIVE LOGITS
     Mujhe
    0.91
     godine
    0.91
     Literally
    0.88
    <unused128>
    0.87
    <unused2136>
    0.87
     nekoliko
    0.87
    <unused2167>
    0.86
    abhavena
    0.86
    MainNav
    0.85
    ujjati
    0.85
    Activations Density 5.939%

    No Known Activations