© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 65007
    Prev
    Next
    INDEX
    Explanations

    swift/objective-c method signatures

    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
     very
    -0.75
    sep
    -0.75
     parecia
    -0.74
     Without
    -0.73
    europa
    -0.72
     dampak
    -0.72
     reloadData
    -0.71
    Cadena
    -0.71
     their
    -0.71
    sys
    -0.70
    POSITIVE LOGITS
    ￬
    0.96
    Started
    0.89
     utilisateur
    0.88
    движи
    0.88
     renderer
    0.85
    THAT
    0.82
    Born
    0.82
     adaptive
    0.81
     conséquent
    0.80
    межу
    0.80
    Activations Density 0.025%

    No Known Activations