© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 7386
    Prev
    Next
    INDEX
    Explanations

    to break or to Church

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

    talking cleaner desktop

    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
     thermally
    0.39
    كلات
    0.39
    𒁕
    0.38
    まつ
    0.37
     policymakers
    0.37
    dfrac
    0.37
     sustainability
    0.37
    ぶり
    0.36
     nonprofits
    0.36
    ポケ
    0.36
    POSITIVE LOGITS
     Wallpaper
    0.55
    Wallpaper
    0.45
    റ്റു
    0.44
     wallpaper
    0.43
    Andrea
    0.42
     talking
    0.41
    Talking
    0.41
     inducement
    0.41
    Ű
    0.41
     wallpapers
    0.40
    Activations Density 0.000%

    No Known Activations