© 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. 38371
    Prev
    Next
    INDEX
    Explanations

    Atraumatic, analysis, about

    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
     cede
    -0.82
     ตัว
    -0.74
    cdonald
    -0.74
     dare
    -0.74
    nacht
    -0.72
    СТВ
    -0.72
     xxi
    -0.72
     endommag
    -0.72
    ське
    -0.72
    zion
    -0.72
    POSITIVE LOGITS
     pittore
    0.82
    samsung
    0.79
     estándares
    0.76
    larınız
    0.76
    rious
    0.76
    silence
    0.75
    ган
    0.75
    Vij
    0.75
    equipe
    0.74
     Iberian
    0.73
    Activations Density 0.001%

    No Known Activations