© 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. 31271
    Prev
    Next
    INDEX
    Explanations

    configuration meta attributes

    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
     WRC
    -0.87
     dimming
    -0.84
     اوم
    -0.81
     Kita
    -0.79
    անդ
    -0.79
     میشه
    -0.79
    Multiplayer
    -0.78
     postId
    -0.76
     eventName
    -0.75
    encre
    -0.74
    POSITIVE LOGITS
     allow
    1.03
     description
    1.02
     max
    0.98
    description
    0.96
     allowed
    0.95
     Allow
    0.94
     tags
    0.94
     settings
    0.93
     enable
    0.92
     auto
    0.90
    Activations Density 0.046%

    No Known Activations