© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43988
    Prev
    Next
    INDEX
    Explanations

    photography

    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
    -4.31
     was
    -3.70
    ?"
    -3.13
    \
    -3.06
    ar
    -2.97
    是
    -2.94
    1
    -2.84
     et
    -2.77
    3
    -2.77
    ,'
    -2.67
    POSITIVE LOGITS
    .
    3.56
    
    3.42
    祼
    3.17
    
    3.16
    鸶
    3.13
     were
    3.06
     vormen
    3.02
    轫
    3.00
    諏
    2.98
    ᮣ
    2.94
    Activations Density 0.005%

    No Known Activations