© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 84451
    Prev
    Next
    INDEX
    Explanations

    doing or did actions

    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
     that
    -2.11
     aéreas
    -1.70
    Untuk
    -1.69
     azioni
    -1.63
    ྜ
    -1.62
     this
    -1.55
    ثم
    -1.55
     mojej
    -1.54
     podoba
    -1.53
     aéreo
    -1.52
    POSITIVE LOGITS
    </strong>
    2.83
    ↵↵
    1.95
     )}
    1.87
    </h1>
    1.61
    ";
    
    1.54
    ’
    1.52
    都在
    1.51
    ".
    1.45
    ).
    1.45
     ´
    1.45
    Activations Density 0.053%

    No Known Activations