© 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. 11886
    Prev
    Next
    INDEX
    Explanations

    Bled, туда

    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
    to
    -2.77
    .
    -2.69
    us
    -2.47
    萏
    -2.30
    );
    -2.28
    which
    -2.22
     многие
    -2.16
     $
    -2.09
    ],
    -2.09
    ly
    -2.08
    POSITIVE LOGITS
    
    2.38
    
    2.33
    ."
    2.22
     Infir
    2.22
    ௅
    2.19
     剧照
    2.03
     Anſ
    2.02
     Berikut
    1.99
    ﮕ
    1.98
    鹮
    1.98
    Activations Density 0.001%

    No Known Activations