© 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. 88583
    Prev
    Next
    INDEX
    Explanations

    selling by Amazon

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

    complex tax or technological situations

    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
     a
    0.62
     it
    0.61
     americana
    0.61
     duplex
    0.55
     cuts
    0.53
     stops
    0.53
     itp
    0.53
     americanos
    0.52
     subcut
    0.51
     baño
    0.50
    POSITIVE LOGITS
    occurrence
    0.55
    students
    0.51
    embrance
    0.50
    ף
    0.48
    defeat
    0.48
    wString
    0.47
    ня
    0.47
     त्याच
    0.47
    áférés
    0.46
    rían
    0.46
    Activations Density 0.002%

    No Known Activations