© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 4736
    Prev
    Next
    INDEX
    Explanations

    instructions and disclaimers

    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
     superhuman
    1.32
    ো
    1.27
     awful
    1.20
     atrocious
    1.20
     behest
    1.18
    യും
    1.17
    ו
    1.15
     hideous
    1.14
     hapless
    1.13
     wretched
    1.13
    POSITIVE LOGITS
     setToDefault
    1.22
     terdapat
    1.22
     généralement
    1.18
    memset
    1.14
    Cette
    1.10
    bold
    1.09
    Ț
    1.09
    <u>
    1.08
    ☛
    1.07
     بالإضافة
    1.06
    Activations Density 0.157%

    No Known Activations