© 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. 60674
    Prev
    Next
    INDEX
    Explanations

    starting or connecting to applications

    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
     этих
    -1.16
    olução
    -1.10
     ursprünglich
    -1.02
    彿
    -1.02
    +"'
    -1.02
     “
    -0.97
    Nokia
    -0.96
    こういう
    -0.94
    Ḏ
    -0.93
    ığımız
    -0.92
    POSITIVE LOGITS
     your
    1.39
     both
    1.17
    İZ
    0.95
     bicara
    0.95
    няются
    0.93
     mắn
    0.93
     制服
    0.92
    jelaskan
    0.91
     our
    0.90
    你和
    0.89
    Activations Density 0.310%

    No Known Activations