© 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. 1925
    Prev
    Next
    INDEX
    Explanations

    names starting with A, E, R

    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
    ampang
    -0.79
     Oku
    -0.78
     maaf
    -0.77
    朕
    -0.77
     Erica
    -0.76
     verand
    -0.75
    íny
    -0.73
     reput
    -0.73
    ท
    -0.73
     sp
    -0.69
    POSITIVE LOGITS
    ஊ
    1.05
    haled
    1.05
    vertisers
    0.98
    Palestinian
    0.94
     Shark
    0.93
     Arab
    0.93
    كويكب
    0.92
    BorderFactory
    0.90
     Egyptian
    0.89
     Arabic
    0.89
    Activations Density 0.071%

    No Known Activations