© 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. 117687
    Prev
    Next
    INDEX
    Explanations

    legal and official proceedings

    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
     obverse
    -0.95
     redress
    -0.85
    ichthys
    -0.82
    出てくる
    -0.81
     nincs
    -0.80
     rebuttal
    -0.78
    什么样的
    -0.78
    OWL
    -0.77
    cademic
    -0.76
     subray
    -0.76
    POSITIVE LOGITS
     verified
    0.98
     certified
    0.93
     certificate
    0.93
     hearing
    0.87
     förr
    0.85
    ORDER
    0.84
     examination
    0.82
    translate
    0.82
    Commission
    0.82
     competente
    0.81
    Activations Density 0.059%

    No Known Activations