© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 166751
    Prev
    Next
    INDEX
    Explanations

    career skills and tools

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

    low effort, low skill

    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
    Negative Logits
     coag
    0.45
    ida
    0.44
    ן
    0.43
    null
    0.41
    egen
    0.41
     אס
    0.40
    sek
    0.40
    ekan
    0.40
    sey
    0.40
    odu
    0.39
    POSITIVE LOGITS
    目の
    0.57
     maximize
    0.49
    ǚ
    0.49
    躓
    0.48
    طبيق
    0.46
     câble
    0.46
    員の
    0.45
    𝕟
    0.45
     télécharger
    0.45
     incentivize
    0.45
    Activations Density 0.001%

    No Known Activations