© 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. 81779
    Prev
    Next
    INDEX
    Explanations

    following clauses

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

    intellectual disability and our results

    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
    irlas
    0.55
    iremos
    0.53
     ฟ้า
    0.50
     แสดง
    0.49
    2
    0.49
    iendo
    0.48
    omerang
    0.48
    arın
    0.47
    asing
    0.47
    แก้ไข
    0.47
    POSITIVE LOGITS
    暦
    0.46
    （
    0.44
    Notably
    0.44
     Notably
    0.43
     mosques
    0.43
     canisters
    0.43
    DVRIP
    0.41
    욕
    0.41
     herbs
    0.41
     andar
    0.39
    Activations Density 0.001%

    No Known Activations