© 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
    3. Gemma-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 2088
    Prev
    Next
    INDEX
    Explanations

    Hungarian cities and language

    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
    <unused709>
    1.45
     acclaimed
    1.43
    <unused512>
    1.41
     egregious
    1.36
    <unused979>
    1.36
     eloquently
    1.34
     willful
    1.34
     delinquent
    1.31
    َہ
    1.31
     Sacramento
    1.30
    POSITIVE LOGITS
     sz
    1.25
     kö
    1.09
    如果
    1.08
    sz
    1.07
     ö
    1.06
    可以
    1.05
    őség
    1.04
     olduğ
    1.03
    ül
    1.03
     poz
    1.01
    Activations Density 0.039%

    No Known Activations