© 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. 147697
    Prev
    Next
    INDEX
    Explanations

    financial quantitative qualifiers

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

    regimes prioritized or suppressed

    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
    Profes
    0.58
    न
    0.51
    dangerous
    0.48
     Satisf
    0.47
     ditulis
    0.46
    Ð
    0.45
    geq
    0.45
     radiator
    0.45
    няў
    0.45
    dengan
    0.45
    POSITIVE LOGITS
    有些人
    0.45
     drying
    0.43
     ايجاد
    0.43
     HomeController
    0.42
    getInput
    0.42
     اين
    0.42
     ща
    0.42
     सूखा
    0.41
    鏤
    0.41
     الحصه
    0.41
    Activations Density 0.000%

    No Known Activations