© 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. 79102
    Prev
    Next
    INDEX
    Explanations

    data types with lengths

    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
     Each
    -0.85
    Each
    -0.81
     আম
    -0.79
     foreach
    -0.78
    еры
    -0.78
    powder
    -0.77
    Več
    -0.76
     does
    -0.74
    出品
    -0.73
    isinstance
    -0.73
    POSITIVE LOGITS
    nvarchar
    0.90
    Ɍ
    0.81
    unicode
    0.80
     родителей
    0.74
     Respuesta
    0.74
     longitudinally
    0.73
    izient
    0.72
    oracle
    0.72
    Stade
    0.72
    tedy
    0.71
    Activations Density 0.002%

    No Known Activations