© 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. 112117
    Prev
    Next
    INDEX
    Explanations

    making a choice of

    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
    }$
    -2.14
    ?”
    -2.09
    {\
    -2.09
    但
    -1.97
    …”
    -1.83
     utilizados
    -1.83
    );
    
    -1.80
    []
    
    -1.80
    ();
    
    -1.77
     entrando
    -1.77
    POSITIVE LOGITS
     of
    1.98
     interpretar
    1.84
     ideas
    1.79
     is
    1.77
    嫆
    1.73
    すれば
    1.70
    ありますが
    1.68
     verrez
    1.68
     pourrez
    1.68
     words
    1.68
    Activations Density 0.005%

    No Known Activations