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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66784
    Prev
    Next
    INDEX
    Explanations

    integral calculus

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    평
    -0.88
     nunca
    -0.84
     angenehm
    -0.84
     if
    -0.83
    ▯
    -0.82
    ان
    -0.79
     natomiast
    -0.77
     zawsze
    -0.77
    kante
    -0.75
    if
    -0.75
    POSITIVE LOGITS
     ještě
    0.99
     ešte
    0.94
    стат
    0.94
    一点点
    0.94
     órg
    0.92
     допомогти
    0.91
    Personendaten
    0.91
    améli
    0.90
    warz
    0.89
    レイン
    0.89
    Activations Density 0.014%

    No Known Activations