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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-16K
    4. 9579
    Prev
    Next
    INDEX
    Explanations

    findings, instructions, and results

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     Wedge
    1.25
    ्टी
    1.20
     наме
    1.15
     Приступљено
    1.14
     Bann
    1.12
     asking
    1.11
    茈
    1.11
     conversaciones
    1.10
     चे
    1.10
     Định
    1.09
    POSITIVE LOGITS
    로
    1.16
    来自
    1.13
    renaline
    1.12
    们的
    1.07
    cyclohex
    1.06
    來自
    1.05
    robe
    1.04
    protein
    1.03
    一半
    1.02
    $>
    1.01
    Activations Density 0.109%

    No Known Activations