© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 1240
    Prev
    Next
    INDEX
    Explanations

    occupation and residence

    np_acts-logits-general · gemini-2.5-flash-lite

    educational and employment qualifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ণিজ্য
    0.36
    onesome
    0.36
    倦
    0.34
    ToPlot
    0.34
     इंस्टॉल
    0.33
    getCql
    0.32
     бли
    0.32
     পরিত্যক্ত
    0.32
    सदीय
    0.31
    Questo
    0.31
    POSITIVE LOGITS
     Doctoral
    0.38
     Sph
    0.37
     Occupation
    0.36
     P
    0.35
     Birth
    0.34
    Occupation
    0.34
     Doctorate
    0.34
     Roller
    0.34
    輥
    0.34
     Teachers
    0.33
    Activations Density 0.000%

    No Known Activations