© 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. 22-GEMMASCOPE-RES-131K
    7. 11115
    Prev
    Next
    INDEX
    Explanations

    special characters and numbers

    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
    <0xF0>
    -1.02
    after
    -1.00
    かな
    -0.96
    çage
    -0.96
     isn
    -0.95
    <0xE2>
    -0.94
    According
    -0.94
    мку
    -0.94
     Deutscher
    -0.94
    それに
    -0.93
    POSITIVE LOGITS
     arşivlendi
    1.02
     and
    1.00
    了自己
    0.95
    ערה
    0.94
    Karel
    0.94
     ませ
    0.93
    paso
    0.93
     навсегда
    0.92
    hellip
    0.91
    خخ
    0.91
    Activations Density 0.001%

    No Known Activations