© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 18015
    Prev
    Next
    INDEX
    Explanations

    adventure obstacle courses

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

    obstacle courses and paintball

    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
    iensis
    0.46
     Knowles
    0.43
     nomen
    0.43
     readership
    0.42
    习惯
    0.40
     JSTOR
    0.40
    習慣
    0.40
    }})$
    0.40
     gardener
    0.40
     dancer
    0.39
    POSITIVE LOGITS
     paintball
    1.08
     Indoor
    1.00
     indoor
    0.99
    Indoor
    0.96
     obstacles
    0.94
     obstacle
    0.93
    indoor
    0.93
     Adventure
    0.91
     adventure
    0.90
    obstacles
    0.88
    Activations Density 0.104%

    No Known Activations