© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 51578
    Prev
    Next
    INDEX
    Explanations

    adjacent word pairs forming phrases

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

    basically, essentially, matrices

    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
     Deck
    0.44
     deck
    0.44
    Deck
    0.43
    $)
    0.42
     endgame
    0.42
     Edgar
    0.41
    बादी
    0.41
     )
    0.40
    $.
    0.40
    ບບ
    0.40
    POSITIVE LOGITS
     ਦਾ
    0.58
    ция
    0.57
     стату
    0.54
     아니라
    0.53
     тариф
    0.52
     спор
    0.52
     முக
    0.52
     تعرف
    0.50
     할인
    0.50
     महंगी
    0.49
    Activations Density 0.000%

    No Known Activations