© 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. 63542
    Prev
    Next
    INDEX
    Explanations

    processes and underlying structures

    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
     konstant
    -0.97
    かえ
    -0.94
     caminho
    -0.92
     eixo
    -0.92
     senhora
    -0.90
     umum
    -0.90
     naudo
    -0.90
     fator
    -0.90
     outros
    -0.90
     et
    -0.90
    POSITIVE LOGITS
    嗞
    1.15
    says
    1.06
    Usually
    1.02
     or
    1.02
     meestal
    1.00
    今日も
    0.98
     interesados
    0.98
     fijne
    0.97
     Usually
    0.95
    未知
    0.95
    Activations Density 0.228%

    No Known Activations