© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 53-GEMMASCOPE-2-RES-262K
    7. 48372
    Prev
    Next
    INDEX
    Explanations

    illegal activity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_53_width_262k_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
     acid
    0.41
     Risks
    0.40
    Risk
    0.40
    碐
    0.39
    jení
    0.39
     risiko
    0.38
     ঝুঁকি
    0.38
    குரு
    0.38
    羣
    0.37
    "]))
    0.37
    POSITIVE LOGITS
    щаем
    0.42
    希望
    0.40
    줬
    0.36
    ccionar
    0.35
    beitet
    0.35
     guarante
    0.35
    heter
    0.35
    eware
    0.35
    췄
    0.35
    izes
    0.34
    Activations Density 0.001%

    No Known Activations