© 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. 10-GEMMASCOPE-RES-131K
    7. 118860
    Prev
    Next
    INDEX
    Explanations

    scarcity and rarity

    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_10/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
    The
    -3.25
    '
    -2.92
    泚
    -2.69
    時間
    -2.67
     –
    -2.56
    There
    -2.31
     dasarnya
    -2.28
    は
    -2.20
    It
    -2.17
    Honestly
    -2.16
    POSITIVE LOGITS
    อื่น
    2.64
    
    2.45
    砹
    2.42
    ');
    2.41
    趼
    2.34
     autres
    2.31
    𖡼
    2.28
    鳢
    2.28
    鴣
    2.27
     calories
    2.23
    Activations Density 0.002%

    No Known Activations