© 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. 127590
    Prev
    Next
    INDEX
    Explanations

    Octopus land modified develop light

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

    recognize suggestion, parenting styles

    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
    定め
    0.55
    来た
    0.53
     immediacy
    0.49
    修正
    0.47
     reloading
    0.47
     babel
    0.47
    ᑯ
    0.46
     इसरो
    0.46
    中所
    0.46
     refroidissement
    0.45
    POSITIVE LOGITS
    ang
    0.54
    jid
    0.52
     Corm
    0.51
     Occup
    0.50
     Mark
    0.50
     Order
    0.50
    _
    0.49
    il
    0.49
     Ama
    0.49
     Ще
    0.49
    Activations Density 0.000%

    No Known Activations