© 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. 111341
    Prev
    Next
    INDEX
    Explanations

    finally followed by event

    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
                
    -1.77
     để
    -1.66
    )$
    -1.65
               
    -1.63
    ar
    -1.62
     żeby
    -1.60
    甚至是
    -1.59
    9
    -1.58
    pecabe
    -1.56
    _{
    -1.55
    POSITIVE LOGITS
     girar
    1.70
    哙
    1.64
    muñ
    1.55
     animada
    1.52
     furg
    1.52
     antena
    1.51
     navegar
    1.51
    UCION
    1.50
     policia
    1.50
     arrancar
    1.48
    Activations Density 0.011%

    No Known Activations