© 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. 54305
    Prev
    Next
    INDEX
    Explanations

    script tags and loci

    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
    ್ಯ
    -0.75
    CTT
    -0.74
     анд
    -0.65
    Fill
    -0.65
    敷
    -0.64
     maman
    -0.63
     kerusakan
    -0.63
     essayer
    -0.63
    مین
    -0.62
     uby
    -0.62
    POSITIVE LOGITS
     fainting
    0.71
    
    0.69
     الدرا
    0.68
    CommandType
    0.65
    Kut
    0.65
    *',
    0.65
    yeong
    0.64
     Dora
    0.64
    umpulan
    0.63
    Engines
    0.63
    Activations Density 0.059%

    No Known Activations