© 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. 115861
    Prev
    Next
    INDEX
    Explanations

    being a fan

    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
     farklı
    -1.11
     different
    -1.10
     χρήση
    -1.09
     a
    -1.09
     amables
    -1.01
    车站
    -1.00
    وارض
    -0.99
     comunica
    -0.98
     looming
    -0.97
     compone
    -0.96
    POSITIVE LOGITS
    boy
    1.74
    atical
    1.54
    boys
    1.40
    boi
    1.39
    fan
    1.34
     fan
    1.24
     CLUB
    1.20
     FAN
    1.17
     of
    1.15
    Boy
    1.13
    Activations Density 0.016%

    No Known Activations