© 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. 73991
    Prev
    Next
    INDEX
    Explanations

    it is clear that

    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
    </i>
    -2.02
    <i>
    -1.81
    </b>
    -1.70
     
    -1.63
        
    -1.63
    า
    -1.63
    ])
    -1.62
     section
    -1.61
    achau
    -1.61
                  
    -1.59
    POSITIVE LOGITS
     that
    3.02
     continúas
    1.70
    、【
    1.62
     demás
    1.60
    歘
    1.59
     akrab
    1.58
     tilby
    1.56
     aktivitet
    1.45
     möjlighet
    1.41
    榀
    1.41
    Activations Density 0.009%

    No Known Activations