© 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. 173815
    Prev
    Next
    INDEX
    Explanations

    3 piece sectionals

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

    renewable energy, ESG, legal, instruction

    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
    stalk
    0.51
    \|,
    0.49
    ार
    0.47
    romantic
    0.46
    <unused1094>
    0.46
    Romantic
    0.45
     ক্রমাগত
    0.45
    searchDisplay
    0.44
     Accessed
    0.44
     HttpServlet
    0.44
    POSITIVE LOGITS
     RESERVE
    0.51
    бата
    0.48
     vegans
    0.46
     “
    0.45
     reserva
    0.44
     المصري
    0.43
     moms
    0.43
    ó
    0.42
     réserve
    0.42
     Cyborg
    0.42
    Activations Density 0.001%

    No Known Activations