© 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. 1504
    Prev
    Next
    INDEX
    Explanations

    green apple, blackcurrant, vanilla

    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
    蓖
    0.47
    篦
    0.46
    瘢
    0.44
    獗
    0.42
     kmeans
    0.40
    畋
    0.40
    蹂
    0.39
    דה
    0.39
    铧
    0.39
     আবি
    0.38
    POSITIVE LOGITS
    lunch
    0.44
     lunch
    0.44
    mapping
    0.43
    imp
    0.39
    Mapping
    0.39
    quiz
    0.38
    list
    0.38
     dinner
    0.37
    lived
    0.37
     perfect
    0.37
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.