© 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. 186796
    Prev
    Next
    INDEX
    Explanations

    breath, hosting, wedding, roofing, dental, insurance

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

    country names, units, historical comparison

    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
    Not in Any Lists

    No Comments

    Negative Logits
     अप्रैल
    0.46
     disseminated
    0.46
     disseminating
    0.46
     disseminate
    0.46
     snowing
    0.44
    ᱮ
    0.44
    вью
    0.44
    ડિયો
    0.44
    𝗯
    0.43
     galloping
    0.43
    POSITIVE LOGITS
    ötet
    0.48
    IZ
    0.48
    ITT
    0.46
    AZ
    0.46
    writer
    0.45
    EST
    0.44
    IK
    0.44
    üm
    0.44
    SZ
    0.44
    EMA
    0.43
    Activations Density 0.001%

    No Known Activations