© 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. 2720
    Prev
    Next
    INDEX
    Explanations

    noun phrase followed by verb

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

    is followed by verbs indicating state or action

    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
     होंगी
    0.45
    你是
    0.44
    ကာ
    0.42
    說是
    0.41
     लगेगा
    0.41
     चलेंगे
    0.40
    你应该
    0.40
     लगेंगे
    0.40
     लगना
    0.39
     whirling
    0.39
    POSITIVE LOGITS
     may
    0.78
     might
    0.77
     gets
    0.72
     was
    0.72
     tends
    0.71
     does
    0.67
     has
    0.67
     would
    0.66
     is
    0.65
     could
    0.65
    Activations Density 0.236%

    No Known Activations