© 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. 168035
    Prev
    Next
    INDEX
    Explanations

    retail, data, knowledge, RX

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

    setting expectations

    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
     mille
    0.43
     surpasses
    0.42
     stops
    0.42
     semifinals
    0.40
    تمل
    0.40
    ازت
    0.40
     yr
    0.39
    违
    0.39
    तात
    0.38
     Romania
    0.38
    POSITIVE LOGITS
     eğer
    0.54
     মে
    0.49
     अगर
    0.48
     மே
    0.48
     অবস্থা
    0.47
    Gw
    0.47
     Ghaz
    0.47
    マガ
    0.47
     желание
    0.47
     ぐらい
    0.46
    Activations Density 0.001%

    No Known Activations