© 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. 137914
    Prev
    Next
    INDEX
    Explanations

    object related to equipment or team ethics

    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
     violations
    0.45
     незакон
    0.45
     поддержка
    0.43
     ilegal
    0.43
     Epis
    0.42
    ა
    0.42
    ា
    0.42
     учун
    0.41
    蓉
    0.41
    зит
    0.41
    POSITIVE LOGITS
    mrow
    0.47
    alpha
    0.46
    タン
    0.45
     Traditions
    0.44
     東
    0.44
     mulut
    0.44
    bao
    0.42
    ভাগের
    0.42
    xlabel
    0.42
    पोज
    0.42
    Activations Density 0.000%

    No Known Activations