© 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. 211550
    Prev
    Next
    INDEX
    Explanations

    governed, table, science

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

    bridge, century, firm, subscription, further

    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
     亻
    0.44
    ørende
    0.43
     Delivery
    0.40
    ipped
    0.40
    αν
    0.39
    贷
    0.39
    ene
    0.39
     Rack
    0.39
    clientX
    0.39
     Marianne
    0.39
    POSITIVE LOGITS
     शास्त्रों
    0.53
     наука
    0.51
     эш
    0.50
     Нау
    0.50
    ாட்டு
    0.50
     новые
    0.50
    𝗜
    0.48
    𝗡
    0.48
    𝗝
    0.48
     eradicate
    0.47
    Activations Density 0.000%

    No Known Activations