© 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. 55912
    Prev
    Next
    INDEX
    Explanations

    emerging, patients, failing, lives

    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
    вард
    0.51
    髡
    0.46
    ማሪ
    0.45
    ές
    0.45
     unemployment
    0.44
    μέ
    0.43
    리
    0.43
     जाएँ
    0.42
    다
    0.42
     masch
    0.42
    POSITIVE LOGITS
     That
    0.49
    ⁃
    0.49
    ingt
    0.48
    anges
    0.45
    got
    0.44
     बंद
    0.43
     Sometimes
    0.43
     ഒറ്റ
    0.42
    hing
    0.42
    zing
    0.41
    Activations Density 0.000%

    No Known Activations