© 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. 66349
    Prev
    Next
    INDEX
    Explanations

    fanfiction or fic

    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
    HStack
    -0.90
     Instagram
    -0.85
     emoji
    -0.84
    retion
    -0.82
    、、
    -0.81
     selfie
    -0.81
     инста
    -0.78
     gerak
    -0.78
     instagram
    -0.75
     pals
    -0.74
    POSITIVE LOGITS
     fic
    1.23
     fanfiction
    1.06
     fanfic
    1.05
     fanart
    1.01
     femmes
    0.93
     fich
    0.90
     fann
    0.90
     fandom
    0.90
    livejournal
    0.89
     squee
    0.88
    Activations Density 0.044%

    No Known Activations