© 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. 43256
    Prev
    Next
    INDEX
    Explanations

    developing their

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

    new purchases

    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
     выво
    0.51
     губерна
    0.49
     falam
    0.49
    的思想
    0.48
    瞩
    0.48
     फेल
    0.46
    ัล
    0.45
    लब
    0.45
    别
    0.44
    历
    0.44
    POSITIVE LOGITS
    コーナー
    0.46
    ဆောင်
    0.42
     ততক্ষণ
    0.42
    activation
    0.42
    oration
    0.41
    uración
    0.40
    引き続き
    0.39
    URAL
    0.38
    すぐに
    0.38
    UTRAL
    0.38
    Activations Density 0.000%

    No Known Activations