© 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. 57893
    Prev
    Next
    INDEX
    Explanations

    professor title used for names

    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
     sketchbook
    -0.88
    oforte
    -0.88
     scouts
    -0.86
     salespeople
    -0.84
    EFIAPI
    -0.84
     craftsmen
    -0.82
    olybdenum
    -0.80
    👐
    -0.79
    сиона
    -0.79
    spray
    -0.79
    POSITIVE LOGITS
     professor
    4.53
     professors
    3.88
     Professor
    3.80
    Professor
    3.61
    professor
    3.48
     Professors
    2.94
     profesor
    2.91
    教授
    2.67
     faculty
    2.59
     academic
    2.42
    Activations Density 0.129%

    No Known Activations