© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 17324
    Prev
    Next
    INDEX
    Explanations

    more details or learn more

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

    sexually suggestive topics

    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_53_width_65k_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
     #
    0.54
     #-
    0.45
     '#
    0.44
    #
    0.43
    name
    0.43
     Name
    0.42
     #"
    0.41
     #'
    0.40
     '#'
    0.39
    #
    0.39
    POSITIVE LOGITS
     palmit
    0.42
    鐲
    0.41
     modular
    0.41
    :],
    0.40
     ক্লিক
    0.40
     settimane
    0.40
    单击
    0.39
     hybr
    0.39
     tıkl
    0.39
     bater
    0.39
    Activations Density 0.000%

    No Known Activations