© 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. 34-GEMMASCOPE-RES-131K
    7. 64190
    Prev
    Next
    INDEX
    Explanations

    programming code and specific phrases

    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_34/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
     acert
    -0.97
    tagHelper
    -0.96
    Ekster
    -0.89
    BufferException
    -0.88
     contratación
    -0.86
    arası
    -0.83
    gın
    -0.83
    æt
    -0.83
     soldadura
    -0.83
     dovr
    -0.82
    POSITIVE LOGITS
     fun
    1.48
    fun
    1.13
     val
    0.94
    val
    0.90
     FUN
    0.86
     poo
    0.81
    runt
    0.78
     '-';
    0.77
    Fun
    0.77
     as
    0.77
    Activations Density 0.002%

    No Known Activations