© 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. 5146
    Prev
    Next
    INDEX
    Explanations

    symbols representing parts or actions

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

    wave basics

    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
    alto
    0.54
    conto
    0.45
    ón
    0.45
     undoubt
    0.45
    虧
    0.42
     り
    0.42
     長
    0.42
     largo
    0.42
    錄
    0.42
    C
    0.41
    POSITIVE LOGITS
     konfigur
    0.59
     adiab
    0.57
    StockDel
    0.55
    '></
    0.54
     trening
    0.53
     grunds
    0.52
     minimale
    0.52
     classiques
    0.52
     klasse
    0.50
    膻
    0.50
    Activations Density 0.001%

    No Known Activations