© 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. 34-GEMMASCOPE-RES-131K
    7. 93543
    Prev
    Next
    INDEX
    Explanations

    before action

    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_34/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
    operation
    -0.71
    емы
    -0.68
    oper
    -0.68
     опера
    -0.66
     operation
    -0.65
    outi
    -0.64
    章节错误
    -0.63
    operators
    -0.62
     发送
    -0.61
     leído
    -0.61
    POSITIVE LOGITS
     mattress
    0.85
     Mattress
    0.80
    passphrase
    0.76
    镯
    0.76
     McF
    0.73
     GPR
    0.73
     Crot
    0.70
    ariate
    0.69
     labai
    0.67
    Ｎ
    0.67
    Activations Density 0.089%

    No Known Activations