© 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. 7664
    Prev
    Next
    INDEX
    Explanations

    actively participate in

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

    participate in

    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
    पश्चिम
    0.46
    jado
    0.46
     マイ
    0.43
    рани
    0.43
     stepping
    0.41
    オ
    0.41
    О
    0.41
    〔
    0.41
    い
    0.40
    マイ
    0.40
    POSITIVE LOGITS
     participar
    0.86
     actively
    0.85
     pleinement
    0.81
     deeln
    0.79
     participa
    0.77
     particip
    0.77
    积极
    0.76
     meaningfully
    0.75
     적극
    0.75
     participe
    0.74
    Activations Density 0.036%

    No Known Activations