© 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. 89668
    Prev
    Next
    INDEX
    Explanations

    negation of physical action or destruction

    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
    highly
    0.49
    Proc
    0.45
    Factor
    0.45
    Bd
    0.44
    },\
    0.44
    platten
    0.44
    Iranian
    0.42
    то
    0.42
    예
    0.42
    Unter
    0.42
    POSITIVE LOGITS
     Soccer
    0.45
     Disputes
    0.45
     Sealed
    0.42
     Rules
    0.42
     Play
    0.41
     e
    0.41
     ș
    0.41
     यहां
    0.41
     Markers
    0.41
    两种
    0.40
    Activations Density 0.005%

    No Known Activations