© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 12785
    Prev
    Next
    INDEX
    Explanations

    related to other words

    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
     مواقع
    0.79
    exceptions
    0.75
    he
    0.74
     vowels
    0.73
     मुख
    0.70
    ok
    0.68
    alternate
    0.67
    \
    0.66
     деца
    0.66
     झग
    0.66
    POSITIVE LOGITS
     també
    1.10
     también
    1.06
     również
    1.05
     também
    1.03
     également
    1.00
     terkait
    0.99
     Beitrag
    0.91
     Related
    0.90
     related
    0.89
    蹭
    0.89
    Activations Density 0.077%

    No Known Activations