© 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. 178575
    Prev
    Next
    INDEX
    Explanations

    struggling with racial matters or damage

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

    license, inequality, travel, win, quote, renovation, noise, review

    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
     demikian
    0.53
     χωρίς
    0.53
    이었다
    0.51
     (…)
    0.50
    මය
    0.48
     نہیں۔
    0.48
     копия
    0.47
    ն
    0.47
     tanpa
    0.47
     아무
    0.46
    POSITIVE LOGITS
    䍧
    0.42
     ions
    0.42
    lde
    0.41
    য়েড
    0.40
    ρο
    0.40
     jazz
    0.40
     painters
    0.39
    GUARD
    0.39
    ଜ
    0.38
    irchen
    0.38
    Activations Density 0.001%

    No Known Activations