© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 34545
    Prev
    Next
    INDEX
    Explanations

    arrow keys and control

    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
     even
    -1.04
     in
    -1.04
     but
    -1.02
     when
    -0.98
     does
    -0.97
    ！）
    -0.91
     at
    -0.91
     so
    -0.88
     has
    -0.88
    ⩽
    -0.87
    POSITIVE LOGITS
     рекомендации
    1.01
    udere
    1.00
    饸
    0.99
     ئ
    0.98
     marié
    0.98
    jska
    0.96
     miniaturka
    0.94
    *;
    0.94
    ときの
    0.93
     différentes
    0.93
    Activations Density 0.000%

    No Known Activations