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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 100278
    Prev
    Next
    INDEX
    Explanations

    fetishistic content

    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_31_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
     Businesses
    0.49
     Marketing
    0.48
    Businesses
    0.48
     Sponsorship
    0.47
    
    0.47
    инг
    0.46
     Advert
    0.46
     Restaurants
    0.45
    荩
    0.45
     Auctions
    0.45
    POSITIVE LOGITS
     cases
    0.62
     experimental
    0.61
     tumor
    0.58
     extracellular
    0.57
     physicists
    0.56
     interfacial
    0.56
     phenomena
    0.56
     superposition
    0.55
     mutations
    0.55
     encounters
    0.54
    Activations Density 0.032%

    No Known Activations