© 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. 107176
    Prev
    Next
    INDEX
    Explanations

    "Q", "Paper", "[", "EPO"

    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
    燴
    -0.78
     large
    -0.76
    étisme
    -0.75
    表彰
    -0.74
    ỏng
    -0.72
     proposals
    -0.71
    谊
    -0.71
    悌
    -0.69
     connection
    -0.69
     housing
    -0.68
    POSITIVE LOGITS
     IRC
    0.89
     Imran
    0.89
     Croydon
    0.89
     Maryam
    0.83
     QS
    0.83
     Elaine
    0.82
     pollin
    0.81
    QS
    0.81
     benef
    0.80
     ktorá
    0.79
    Activations Density 0.008%

    No Known Activations