© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 100685
    Prev
    Next
    INDEX
    Explanations

    precious valuable things

    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
    😚
    -2.48
     juft
    -2.36
    💖
    -2.31
    💓
    -2.31
    ⢊
    -2.28
    💗
    -2.28
    ";
    -2.28
     laft
    -2.25
    
    -2.23
    倅
    -2.23
    POSITIVE LOGITS
     
    3.39
    </em>
    2.98
    </h4>
    2.77
     Utilizing
    2.67
     scant
    2.58
    will
    2.50
     —
    2.38
    ly
    2.33
    又不
    2.33
     maintenant
    2.31
    Activations Density 0.002%

    No Known Activations