© 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. 2307
    Prev
    Next
    INDEX
    Explanations

    sentence end followed by description

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

    AI assistant refusal

    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
     行っ
    0.43
     あれ
    0.42
     minded
    0.40
     ruj
    0.39
     みたい
    0.38
     चौटाला
    0.38
     だっ
    0.38
    摳
    0.38
     言っ
    0.37
    ㄺ
    0.37
    POSITIVE LOGITS
     Package
    0.53
    ✿
    0.50
    ❀
    0.47
     Sizes
    0.46
     ♥
    0.46
    featuring
    0.45
     please
    0.44
     Size
    0.44
    ◕
    0.44
    ▬
    0.44
    Activations Density 0.040%

    No Known Activations