© 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. 87219
    Prev
    Next
    INDEX
    Explanations

    fashion show

    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
    lii
    -0.84
    торая
    -0.82
    ardes
    -0.82
     know
    -0.81
    rippa
    -0.80
     byg
    -0.79
     sosyal
    -0.79
    🔄
    -0.78
    зани
    -0.78
    мото
    -0.77
    POSITIVE LOGITS
    Yaz
    0.87
     закончи
    0.81
    yuk
    0.79
    楽し
    0.75
    accus
    0.74
     keuntungan
    0.73
    Leve
    0.73
    覗
    0.73
     Criticism
    0.72
     hated
    0.71
    Activations Density 0.002%

    No Known Activations