© 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. 34-GEMMASCOPE-RES-131K
    7. 76719
    Prev
    Next
    INDEX
    Explanations

    programming, code, configuration, application names

    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
    銅
    -0.75
    ئی
    -0.74
    golang
    -0.73
    [...,
    -0.66
     Mum
    -0.65
    rington
    -0.65
    铜
    -0.64
     گو
    -0.63
    kotlin
    -0.63
     randint
    -0.63
    POSITIVE LOGITS
     جدا
    0.71
     Sond
    0.66
    addContainerGap
    0.66
     Ponte
    0.65
     بن
    0.63
     Bn
    0.63
     kredit
    0.63
    peng
    0.63
    ongiorno
    0.62
     phoneNumber
    0.61
    Activations Density 0.071%

    No Known Activations