© 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. 91742
    Prev
    Next
    INDEX
    Explanations

    market reports and studies

    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
     anunció
    -0.81
    ✺
    -0.74
    тай
    -0.73
    即使
    -0.72
     نگاه
    -0.72
     look
    -0.72
    짝
    -0.72
    cerely
    -0.71
    BONUS
    -0.68
     malgré
    -0.67
    POSITIVE LOGITS
     Inquirer
    0.83
    了下去
    0.81
    ceptual
    0.80
     Tumble
    0.79
    GetCurrent
    0.76
     provincia
    0.75
     Detroit
    0.74
    SerializedName
    0.73
     учет
    0.73
     Enquiry
    0.73
    Activations Density 0.003%

    No Known Activations