© 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. 91404
    Prev
    Next
    INDEX
    Explanations

    code snippets and technical terms

    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
    ocarditis
    -0.89
    𝗉
    -0.85
     matemáticas
    -0.84
    潇
    -0.82
    :}
    -0.82
     terpaksa
    -0.82
     każdy
    -0.81
    宜蘭
    -0.81
    坞
    -0.80
    ઃ
    -0.80
    POSITIVE LOGITS
     instead
    0.82
     insisting
    0.77
    
    0.77
    Jing
    0.77
     bumble
    0.75
     urč
    0.74
     hardworking
    0.74
    ल्स
    0.73
    벽
    0.71
    Melan
    0.70
    Activations Density 0.000%

    No Known Activations