© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 182089
    Prev
    Next
    INDEX
    Explanations

    botnet floods DNS

    np_acts-logits-general · gemini-2.5-flash-lite

    agricultural, about, status

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PCS
    0.45
    🙎
    0.44
    Gc
    0.42
    γραφή
    0.42
    pV
    0.42
    ("${
    0.41
     athlet
    0.41
    颗
    0.41
     Headache
    0.41
    ार्थियों
    0.41
    POSITIVE LOGITS
     polymers
    0.52
     nowadays
    0.48
     tô
    0.48
     têm
    0.47
     binaries
    0.47
     Зак
    0.47
     powders
    0.47
     inaccuracies
    0.46
     беру
    0.46
     paves
    0.46
    Activations Density 0.002%

    No Known Activations