© 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. 31851
    Prev
    Next
    INDEX
    Explanations

    order ID retrieval

    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
     авто
    -0.69
     holding
    -0.67
     access
    -0.67
     мъ
    -0.65
     link
    -0.65
     name
    -0.64
     update
    -0.64
     five
    -0.64
     competitive
    -0.64
    危害
    -0.63
    POSITIVE LOGITS
    Kaz
    0.72
    nici
    0.69
     begotten
    0.69
    bura
    0.69
     Caleb
    0.68
    MSO
    0.67
     پایان
    0.67
     aerop
    0.67
     Missoula
    0.67
     ثلاثة
    0.67
    Activations Density 0.112%

    No Known Activations