© 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. 183212
    Prev
    Next
    INDEX
    Explanations

    mental health and personal information

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

    life or undo management

    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
     watery
    0.47
    いわ
    0.45
     klasik
    0.45
     moan
    0.45
    வார்கள்
    0.44
     lungs
    0.43
     বাতাসে
    0.43
    ڭ
    0.43
    glasses
    0.42
    牀
    0.42
    POSITIVE LOGITS
    formData
    0.42
     EDGE
    0.42
     juvenile
    0.42
     तैनाती
    0.42
     specified
    0.40
     Canopy
    0.40
    videoId
    0.40
     freshman
    0.39
     disclosed
    0.39
     JFK
    0.39
    Activations Density 0.004%

    No Known Activations