© 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-3-27B-IT
    3. 53-GEMMASCOPE-2-RES-262K
    4. 18559
    Prev
    Next
    INDEX
    Explanations

    erotic romance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_53_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ppro
    0.43
    acter
    0.42
     frightening
    0.41
    夥
    0.40
    бенок
    0.40
     childlike
    0.40
    ersonal
    0.39
    伙
    0.39
     scary
    0.38
     vaik
    0.38
    POSITIVE LOGITS
     romance
    1.12
     Romance
    1.02
     romances
    0.83
     роман
    0.80
    Rom
    0.74
     spicy
    0.72
     romant
    0.71
     rom
    0.70
     Spicy
    0.66
     romantic
    0.65
    Activations Density 0.063%

    No Known Activations