© 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. 185675
    Prev
    Next
    INDEX
    Explanations

    security and access policies

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

    understanding it

    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
     สอบ
    0.54
     Обе
    0.51
    itius
    0.50
    зулта
    0.50
    </h6>
    0.49
    ningen
    0.49
     fino
    0.48
    inito
    0.48
    ึง
    0.48
     Еще
    0.47
    POSITIVE LOGITS
     establish
    0.53
    殇
    0.46
     germinate
    0.45
     schwier
    0.44
    ))&&(
    0.44
    dynam
    0.43
     ಅದರ
    0.43
     discouraged
    0.43
    KIA
    0.42
     eradicate
    0.41
    Activations Density 0.000%

    No Known Activations