© 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. 193002
    Prev
    Next
    INDEX
    Explanations

    word followed by related word

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

    likely to exceed limits

    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
    ์
    0.44
    Clinic
    0.44
    CAD
    0.43
    Ⅺ
    0.43
    てください
    0.43
     Qaeda
    0.43
    クライ
    0.42
    事前
    0.42
    roductive
    0.41
    ธ
    0.41
    POSITIVE LOGITS
     lactose
    0.51
     realises
    0.47
     oxidizing
    0.46
     rejuven
    0.46
    วิ่ง
    0.46
     aldehydes
    0.45
    휘
    0.45
     capitalism
    0.45
     ऑक्सी
    0.45
    рах
    0.44
    Activations Density 0.001%

    No Known Activations