© 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. 31-GEMMASCOPE-2-RES-262K
    7. 82979
    Prev
    Next
    INDEX
    Explanations

    terrorism and incitement

    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_31_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
    sthe
    0.48
    hombre
    0.46
    impi
    0.46
    queleto
    0.45
    heaven
    0.44
     일이
    0.43
    it
    0.43
    ף
    0.42
    ique
    0.42
    ੍ਹਾਂ
    0.42
    POSITIVE LOGITS
     fasten
    0.49
    PTMR
    0.48
    ご確認
    0.48
     amalgamation
    0.45
    ীবন
    0.44
    ご購入
    0.44
    皋
    0.44
     Formulation
    0.44
    一部分
    0.43
     chirurg
    0.43
    Activations Density 0.004%

    No Known Activations