© 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. 4780
    Prev
    Next
    INDEX
    Explanations

    security patches, patches, adhesive patch

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

    security patches and updates

    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
    ុក
    0.42
    StoredKeys
    0.41
     बोस
    0.40
    陖
    0.40
    击
    0.39
     هوا
    0.37
     Shuk
    0.37
    擎
    0.37
    navbarSupported
    0.37
     saisir
    0.37
    POSITIVE LOGITS
     patch
    4.63
    patch
    4.34
     Patch
    4.31
     patches
    4.25
    Patch
    4.25
     PATCH
    3.97
     patching
    3.81
    patches
    3.77
    PATCH
    3.72
     patched
    3.72
    Activations Density 0.095%

    No Known Activations