© 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. 92889
    Prev
    Next
    INDEX
    Explanations

    internet corporation for assigned names and numbers

    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
     registered
    -0.73
    ストリー
    -0.72
     salario
    -0.72
     Newtonsoft
    -0.71
     dioces
    -0.71
     currentState
    -0.70
     Poon
    -0.68
    SHI
    -0.67
     calculates
    -0.67
     specify
    -0.67
    POSITIVE LOGITS
     Donuts
    0.98
    IANA
    0.94
     GAC
    0.91
    clad
    0.82
    community
    0.81
    Community
    0.80
    GAC
    0.79
    笑的
    0.78
     community
    0.77
    "@
    0.77
    Activations Density 0.024%

    No Known Activations