© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 75680
    Prev
    Next
    INDEX
    Explanations

    keyboard layouts

    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
    Moore
    -0.78
    siyon
    -0.78
     Agric
    -0.75
    套
    -0.75
    Geoff
    -0.68
    olum
    -0.66
    setValue
    -0.66
     جمه
    -0.65
     قوات
    -0.65
     Jest
    -0.65
    POSITIVE LOGITS
    antine
    0.63
     todas
    0.63
     FEATURE
    0.63
     Featured
    0.61
     shuffling
    0.60
     Vienna
    0.59
     Todas
    0.59
    inados
    0.58
     TypeError
    0.58
     criticize
    0.58
    Activations Density 0.083%

    No Known Activations