© 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. 167915
    Prev
    Next
    INDEX
    Explanations

    Jekyll and Hyde

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

    exploring new actions

    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
     asl
    0.49
     Kari
    0.47
     Hoffmann
    0.47
     korun
    0.45
     Breite
    0.45
     Oviedo
    0.44
    FileInputExcel
    0.44
     Zoll
    0.44
     絵
    0.44
     الرئيسي
    0.43
    POSITIVE LOGITS
     менедж
    0.49
     Redis
    0.48
    Redis
    0.46
    क्र
    0.44
    𝙔
    0.44
    Nuclear
    0.43
    삶
    0.42
     techniques
    0.42
    Thousands
    0.42
    NUCLEAR
    0.41
    Activations Density 0.000%

    No Known Activations