© 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. 22-GEMMASCOPE-RES-131K
    7. 27476
    Prev
    Next
    INDEX
    Explanations

    names and origins

    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_22/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
    '
    -1.45
     "
    -1.42
    a
    -1.39
    "
    -1.29
    I
    -1.27
    j
    -1.27
     should
    -1.23
    L
    -1.23
    O
    -1.20
    T
    -1.19
    POSITIVE LOGITS
    Spesifikasi
    1.56
     ekolog
    1.55
     tunik
    1.50
    
    1.49
     terapi
    1.48
     diren
    1.48
    Bahan
    1.46
     camiset
    1.45
    Penjelasan
    1.45
     abstrak
    1.45
    Activations Density 0.007%

    No Known Activations