© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 2589
    Prev
    Next
    INDEX
    Explanations

    Niro EV, Airbus, puncture, irritation

    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_9_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
    ت
    2.04
    at
    1.71
     inception
    1.68
    ায়
    1.50
    Granted
    1.48
    де
    1.47
    तरी
    1.46
    gados
    1.44
    ਦਰ
    1.42
    াই
    1.41
    POSITIVE LOGITS
    OURCES
    1.64
    ری
    1.60
    그러나
    1.55
    맛집
    1.54
    등
    1.51
    그래서
    1.51
     ώστε
    1.51
     yaad
    1.51
    杷
    1.48
    ्
    1.47
    Activations Density 0.000%

    No Known Activations