© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 1808
    Prev
    Next
    INDEX
    Explanations

    in short summary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_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
     দ্বিত
    0.57
     buttery
    0.54
    <0xBC>
    0.54
     Außerdem
    0.52
    asons
    0.52
     cannon
    0.52
    osex
    0.51
     second
    0.51
    Secondly
    0.50
     gut
    0.50
    POSITIVE LOGITS
    言
    0.93
     palavras
    0.73
     fala
    0.73
    Voice
    0.71
     Talking
    0.70
     Voice
    0.69
     voces
    0.69
    Words
    0.68
    聲
    0.68
     হাইড্রোক
    0.67
    Activations Density 0.277%

    No Known Activations