© 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. 64497
    Prev
    Next
    INDEX
    Explanations

    azure ARM templates

    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
     verfolgen
    -0.77
     Mitteln
    -0.74
    Jawab
    -0.73
     verfü
    -0.73
     commerciali
    -0.72
    鮑
    -0.72
    话
    -0.71
     насле
    -0.71
    力を
    -0.70
     большого
    -0.70
    POSITIVE LOGITS
     Kartu
    0.77
     долго
    0.75
     enactment
    0.73
     menace
    0.73
    lived
    0.71
     recapit
    0.70
    LEV
    0.70
     scap
    0.69
    бири
    0.69
     REACH
    0.69
    Activations Density 0.035%

    No Known Activations