© 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. 92021
    Prev
    Next
    INDEX
    Explanations

    certificate extension issuer critical

    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
     intStringLen
    -0.84
    氘
    -0.75
    uxi
    -0.75
     TextInput
    -0.75
     duplex
    -0.74
    辟
    -0.71
     następnie
    -0.70
     transpose
    -0.69
     במס
    -0.69
    iros
    -0.69
    POSITIVE LOGITS
    extension
    0.99
     extensions
    0.93
     extension
    0.91
    extensions
    0.89
    tbs
    0.79
     issuer
    0.78
    Critical
    0.77
    issuer
    0.76
     Extensions
    0.75
     critical
    0.75
    Activations Density 0.031%

    No Known Activations