© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 69848
    Prev
    Next
    INDEX
    Explanations

    Testimonials, Payment dates, copy

    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
    debit
    -0.83
    фера
    -0.75
    чу
    -0.75
     spiritu
    -0.73
     caoutchouc
    -0.73
    mood
    -0.72
     distin
    -0.71
    ឯ
    -0.71
     Č
    -0.70
     salient
    -0.70
    POSITIVE LOGITS
    uelto
    0.79
    лір
    0.78
    ekt
    0.76
    9
    0.75
    acle
    0.74
    q
    0.73
    َه
    0.72
     Francji
    0.72
    꿍
    0.71
    беріга
    0.71
    Activations Density 0.005%

    No Known Activations