© 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. 199254
    Prev
    Next
    INDEX
    Explanations

    salesman recognizes, your air, PLLC

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

    cultural significance

    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
    ಾ
    0.54
    går
    0.49
     pengaruh
    0.47
    happy
    0.46
     bekom
    0.46
    gister
    0.46
    𝔂
    0.45
     disobey
    0.45
    まる
    0.44
    oleh
    0.44
    POSITIVE LOGITS
            
    0.48
    ță
    0.48
    ()+"
    0.47
    =["
    0.43
     cooperatives
    0.43
    াবাদ
    0.43
    udes
    0.42
     deftly
    0.41
     فو
    0.40
    ToOne
    0.40
    Activations Density 0.000%

    No Known Activations