© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 43335
    Prev
    Next
    INDEX
    Explanations

    words beginning with coll

    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
    ↵↵
    -3.08
    But
    -2.67
    );
    
    -2.38
     To
    -2.33
    This
    -2.23
    ඤ
    -2.20
     — 
    -2.19
    .
    -2.17
    And
    -2.14
    So
    -2.13
    POSITIVE LOGITS
    
    2.53
    みんなで
    2.45
    ]
    2.38
    莚
    2.34
     helicópter
    2.33
     nemici
    2.28
     玄関
    2.27
     rác
    2.25
    他已经
    2.22
     installment
    2.20
    Activations Density 0.003%

    No Known Activations