© 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. 44648
    Prev
    Next
    INDEX
    Explanations

    Dickinson, Hutchinson, Carlisle institutions

    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
    梣
    -2.64
     humeur
    -2.64
    Ꮉ
    -2.48
     当
    -2.41
     odeur
    -2.38
    
    -2.34
    '
    -2.31
    癆
    -2.30
    岿
    -2.28
    }$,
    -2.23
    POSITIVE LOGITS
    姈
    2.55
    ’
    2.52
     Then
    2.45
    s
    2.14
     gewinnt
    2.13
     nhung
    2.11
    ཽ
    2.11
    ⢅
    2.09
     również
    2.09
     tamén
    2.03
    Activations Density 0.002%

    No Known Activations