© 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. 178155
    Prev
    Next
    INDEX
    Explanations

    phrases like `can help` or `pay for`

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

    talk about

    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
     الحمد
    0.52
     شیخ
    0.51
    ңы
    0.51
     اور
    0.49
     økonom
    0.49
     ی
    0.47
     ड
    0.46
    ྕ
    0.45
     امیر
    0.45
    นู
    0.45
    POSITIVE LOGITS
     pulverized
    0.55
    ᱓
    0.53
     smuggled
    0.52
    ，
    0.52
    其中
    0.52
     ionic
    0.50
     ingested
    0.47
     trivalent
    0.47
    reactant
    0.47
    soluble
    0.47
    Activations Density 0.000%

    No Known Activations