© 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. 22-GEMMASCOPE-RES-131K
    4. 35833
    Prev
    Next
    INDEX
    Explanations

    express hope for alternatives

    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_22/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
     поэтому
    -0.92
     Sitemap
    -0.90
     therefore
    -0.88
     Поэтому
    -0.85
    ۋ
    -0.85
     jojo
    -0.83
     now
    -0.83
    YSQL
    -0.80
     Avez
    -0.79
    astră
    -0.79
    POSITIVE LOGITS
     otherwise
    1.38
    otherwise
    1.20
     else
    1.09
    fingers
    1.06
     fingers
    1.06
     Otherwise
    1.02
     inaczej
    0.93
    Otherwise
    0.93
    acke
    0.91
    否则
    0.90
    Activations Density 0.054%

    No Known Activations