© 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. 60006
    Prev
    Next
    INDEX
    Explanations

    specific entities and names

    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
     });
    
    -2.59
    ).
    -2.33
     }).
    -2.22
     για
    -2.19
     }),
    -2.14
    ");
    -2.11
    </h2>
    -2.11
     Ingeniería
    -2.09
     tidak
    -2.00
     acepción
    -1.99
    POSITIVE LOGITS
     手绘
    2.44
     they
    2.39
    {
    2.20
    衚
    2.20
     небольшой
    2.19
    其妙
    2.19
     красивый
    2.13
    ar
    2.05
     desenli
    2.02
    『
    1.95
    Activations Density 0.004%

    No Known Activations