© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 76393
    Prev
    Next
    INDEX
    Explanations

    authentication path sequences

    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
    POLL
    -0.76
    甩
    -0.73
     Servant
    -0.73
    irdre
    -0.71
     Spalding
    -0.70
     Wok
    -0.69
     vot
    -0.69
    Emission
    -0.68
     Pdf
    -0.68
    lk
    -0.67
    POSITIVE LOGITS
    适用于
    0.81
    brigens
    0.77
     sagrado
    0.77
     warden
    0.75
    keyColumn
    0.73
     reciclado
    0.73
     Digest
    0.73
    napp
    0.73
    頃に
    0.72
    naw
    0.72
    Activations Density 0.028%

    No Known Activations