© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103491
    Prev
    Next
    INDEX
    Explanations

    Matthias Christian sashimi disinformation Nanjing

    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
     dà
    -2.92
     остальные
    -2.86
    螣
    -2.66
     peut
    -2.59
    鬭
    -2.58
    
    -2.58
     gebunden
    -2.55
     atau
    -2.53
    𓁹
    -2.53
     gewi
    -2.52
    POSITIVE LOGITS
    at
    2.70
    s
    2.58
     is
    2.45
    ??
    2.33
    ременно
    2.20
    Однако
    2.17
    と書
    2.14
    ஂ
    2.14
    providedIn
    2.14
     descrit
    2.14
    Activations Density 0.002%

    No Known Activations