© 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. 56117
    Prev
    Next
    INDEX
    Explanations

    sensory connections and potential damage

    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
    Corners
    0.53
    तम
    0.50
    Zero
    0.50
    Contin
    0.48
    max
    0.47
    stion
    0.47
    Plan
    0.46
    f
    0.46
    Square
    0.43
     That
    0.43
    POSITIVE LOGITS
     experimented
    0.47
     aikana
    0.46
    <0x95>
    0.45
    <0xAD>
    0.45
     могли
    0.44
     jakim
    0.44
     아니라
    0.44
    还需要
    0.44
     konnten
    0.44
     damaged
    0.43
    Activations Density 0.001%

    No Known Activations