© 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. 59524
    Prev
    Next
    INDEX
    Explanations

    electronic component values and descriptions

    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
    πάρχ
    -0.82
     lend
    -0.79
    reflection
    -0.75
    rira
    -0.73
     Umgebung
    -0.71
     {-
    -0.71
    requestCode
    -0.71
     развитие
    -0.71
     والح
    -0.71
    rowave
    -0.70
    POSITIVE LOGITS
     William
    0.82
    udesta
    0.81
     fabrik
    0.79
    aliere
    0.75
    ಝ
    0.75
    actose
    0.74
     debout
    0.73
    Sistem
    0.72
     idee
    0.70
     koll
    0.70
    Activations Density 0.021%

    No Known Activations