© 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. 93088
    Prev
    Next
    INDEX
    Explanations

    trained peer and volunteer roles

    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
     screenwriter
    -0.88
     psychiatrists
    -0.86
    医生
    -0.85
     vegetarians
    -0.84
     إل
    -0.83
     innovator
    -0.82
    iqué
    -0.79
    仪式
    -0.79
     psychiatrist
    -0.79
     contestants
    -0.77
    POSITIVE LOGITS
     trained
    1.97
     volunteer
    1.38
    trained
    1.37
     Trained
    1.27
     appointed
    1.26
    Trained
    1.24
     designated
    1.22
     certified
    1.18
     coaches
    1.17
     team
    1.15
    Activations Density 0.071%

    No Known Activations