© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 226471
    Prev
    Next
    INDEX
    Explanations

    connective tissue

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    defendant
    0.54
    ip
    0.46
    Defendant
    0.45
    grav
    0.44
    و
    0.44
    ANNOT
    0.44
    监督
    0.43
    ро
    0.42
    E
    0.41
    Dat
    0.41
    POSITIVE LOGITS
    য়াছে
    0.53
     neka
    0.50
     okula
    0.48
    晧
    0.47
     நவ
    0.46
    芏
    0.46
    ្ខ
    0.46
     thí
    0.45
     škol
    0.45
    ⴷ
    0.45
    Activations Density 0.001%

    No Known Activations