© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 80338
    Prev
    Next
    INDEX
    Explanations

    harmful content and planning

    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
    Negative Logits
    k
    0.48
    5
    0.46
    q
    0.42
    מ
    0.42
     nagging
    0.41
    4
    0.41
    फिल्म
    0.41
     impedir
    0.41
    th
    0.40
    6
    0.40
    POSITIVE LOGITS
    ولت
    0.45
    牺
    0.45
    ementerian
    0.43
     IntegerValue
    0.41
    🕣
    0.41
     बनाई
    0.41
    okane
    0.40
    配备
    0.40
    ModuleManager
    0.39
    umination
    0.39
    Activations Density 0.006%

    No Known Activations