© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48373
    Prev
    Next
    INDEX
    Explanations

    Technical terms (command, message, code)

    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
    AspNetCore
    -0.82
    ဒ
    -0.81
    utched
    -0.78
    𝗋
    -0.76
     Geschenk
    -0.74
    struktion
    -0.73
    ০
    -0.72
    poche
    -0.71
    ışık
    -0.70
    aise
    -0.70
    POSITIVE LOGITS
     обучения
    0.77
    }}:
    0.76
     исполь
    0.76
    ställning
    0.73
    拼接
    0.72
    もありました
    0.71
    ⽅
    0.71
     wan
    0.71
    proken
    0.70
    そうだ
    0.69
    Activations Density 0.005%

    No Known Activations