© 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. 13315
    Prev
    Next
    INDEX
    Explanations

    suspicious unusual inconsistencies

    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
    hankelijk
    0.89
    糟
    0.81
    汚
    0.80
    лам
    0.74
     tappa
    0.72
    gaan
    0.72
    വസ്ഥ
    0.71
    quette
    0.70
    ‬‬
    0.69
    estimating
    0.69
    POSITIVE LOGITS
     suspiciously
    2.14
     suspicious
    1.78
     unusually
    1.41
     anormal
    1.41
     Mysterious
    1.40
     sospe
    1.40
     unexplained
    1.38
     mysteriously
    1.36
     mysterious
    1.35
     abnormally
    1.35
    Activations Density 0.250%

    No Known Activations