© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 11137
    Prev
    Next
    INDEX
    Explanations

    romantic suspense novels

    np_acts-logits-general · gemini-2.5-flash-lite

    romance and romantic stories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    各位同學
    0.52
     subsurface
    0.49
     বিস্ফ
    0.47
     JUnit
    0.45
    缽
    0.45
     человеку
    0.44
    朮
    0.44
     polyethylene
    0.43
     филосо
    0.43
    南極
    0.43
    POSITIVE LOGITS
     romance
    0.86
     Romance
    0.85
     romances
    0.75
    💋
    0.70
    💕
    0.64
     romant
    0.63
     Regency
    0.61
     💕
    0.61
    💞
    0.59
    爱情
    0.58
    Activations Density 0.137%

    No Known Activations