© 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. 9587
    Prev
    Next
    INDEX
    Explanations

    numerical lists and code

    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
    ሣ
    0.44
    चालित
    0.42
    凿
    0.40
    Რ
    0.40
    udsman
    0.39
    ocsát
    0.39
    स्कार
    0.38
    rible
    0.38
    opatra
    0.38
    कने
    0.38
    POSITIVE LOGITS
     progressively
    0.45
     Deng
    0.44
     Pune
    0.44
     gil
    0.43
     Kag
    0.43
    進
    0.42
     SE
    0.41
     Increasingly
    0.41
     E
    0.40
     seb
    0.40
    Activations Density 0.008%

    No Known Activations