© 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. 63617
    Prev
    Next
    INDEX
    Explanations

    M&N Mattress company

    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
     Verbesserung
    -0.92
     rancho
    -0.87
     unsure
    -0.86
     kalan
    -0.85
     fuper
    -0.84
    同じく
    -0.84
     idyl
    -0.84
     Änderung
    -0.82
     poffe
    -0.82
    長的
    -0.82
    POSITIVE LOGITS
    sianic
    0.81
     仲
    0.81
     ABSOL
    0.77
    pI
    0.75
     Canary
    0.75
    蚜
    0.74
    waan
    0.73
     ortaya
    0.73
    quitos
    0.73
     farmacé
    0.73
    Activations Density 0.083%

    No Known Activations