© 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. 53873
    Prev
    Next
    INDEX
    Explanations

    Elba, voice, mobile, adir, now, series

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

    DoS attack and related concepts

    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
    家的
    0.50
    奇
    0.50
    ദം
    0.48
    ্লা
    0.48
    Buenos
    0.48
    Interfaz
    0.48
    Gian
    0.47
    Ster
    0.46
     Buenas
    0.46
     anum
    0.45
    POSITIVE LOGITS
    ksh
    0.54
    },
    0.48
    adays
    0.46
    },\
    0.44
     helicopters
    0.43
     дизай
    0.43
    tt
    0.42
    '),
    0.42
    '?
    0.42
     plumage
    0.41
    Activations Density 0.000%

    No Known Activations