© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44949
    Prev
    Next
    INDEX
    Explanations

    Eastern Standard Time

    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_10/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
     
    -3.13
    1
    -3.02
    3
    -2.89
     Возможно
    -2.52
    Initially
    -2.50
    他
    -2.47
     Конечно
    -2.44
    This
    -2.41
     Хорошо
    -2.38
     Possibly
    -2.34
    POSITIVE LOGITS
    珢
    3.19
    峄
    2.70
    ſſen
    2.67
    
    2.67
    ᯅ
    2.64
    ቍ
    2.61
    ⬯
    2.53
     онъ
    2.50
    bowl
    2.48
     姆
    2.45
    Activations Density 0.002%

    No Known Activations