© 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. 107899
    Prev
    Next
    INDEX
    Explanations

    structural components

    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
     Torneo
    -0.84
    ⡟
    -0.77
     प्रदान
    -0.77
     repente
    -0.74
    женной
    -0.73
    ઇ
    -0.72
    Dsl
    -0.72
     pornography
    -0.71
     prohi
    -0.71
     phù
    -0.71
    POSITIVE LOGITS
     structures
    4.13
     structure
    3.64
     Structures
    3.44
     structural
    3.30
    structures
    3.11
    structure
    2.95
     estructuras
    2.89
    结构
    2.88
     Structure
    2.86
    Structures
    2.81
    Activations Density 0.082%

    No Known Activations