© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 103435
    Prev
    Next
    INDEX
    Explanations

    romance novels and authors

    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
    chargez
    -0.89
     SECTION
    -0.88
    SECTION
    -0.84
     Gelb
    -0.83
     childrens
    -0.82
    駅
    -0.82
    InjectMocks
    -0.79
    metrics
    -0.76
    стояние
    -0.74
    を用
    -0.74
    POSITIVE LOGITS
     romance
    1.70
    romance
    1.24
     Romance
    1.21
    Romance
    1.19
     romances
    1.15
     paranormal
    1.15
     romantic
    1.07
     regency
    1.02
     Regency
    1.02
     authors
    1.00
    Activations Density 0.062%

    No Known Activations