© 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. 90763
    Prev
    Next
    INDEX
    Explanations

    units or measurements

    np_acts-logits-general · gemini-2.5-flash-lite

    sharing positive memories

    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
    ↵
    0.45
    வு
    0.45
    평
    0.44
     rash
    0.41
     평
    0.41
    qx
    0.40
    erais
    0.40
     앞으로
    0.40
     $(
    0.39
    今後
    0.38
    POSITIVE LOGITS
    𝙫
    0.57
     juguete
    0.54
    ንዳንድ
    0.53
     cárcel
    0.52
     einzige
    0.50
     regelmäßig
    0.50
     einiger
    0.49
     материала
    0.49
     regelmatig
    0.48
     materiál
    0.48
    Activations Density 0.002%

    No Known Activations