© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 65758
    Prev
    Next
    INDEX
    Explanations

    "$schema" or "$Id" starts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     already
    -1.09
     сті
    -1.00
     czerwony
    -0.96
     хви
    -0.94
     apricot
    -0.91
     anderes
    -0.90
     alone
    -0.90
    ikations
    -0.89
     Detta
    -0.88
     вже
    -0.85
    POSITIVE LOGITS
    ().
    1.16
    $.
    1.06
     borra
    0.99
    Jahre
    0.93
    Horrible
    0.92
    ⭏
    0.92
    ̦
    0.90
    |^{
    0.90
    خواندن
    0.90
     ")");
    0.89
    Activations Density 0.055%

    No Known Activations