© 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. 34-GEMMASCOPE-RES-131K
    7. 108394
    Prev
    Next
    INDEX
    Explanations

    Server Timestamp, Advantages Of, Ionization

    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
    ZM
    -0.77
    Stream
    -0.76
     acessar
    -0.75
    FailureListener
    -0.75
     puteți
    -0.74
     lustrous
    -0.73
     alcançar
    -0.73
     タグ
    -0.72
    andal
    -0.71
     guided
    -0.70
    POSITIVE LOGITS
     task
    0.85
     Task
    0.83
     porte
    0.79
    он
    0.77
    addOn
    0.77
     techn
    0.75
     Maureen
    0.75
     toujours
    0.75
     donar
    0.75
     devam
    0.72
    Activations Density 0.021%

    No Known Activations