© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 18071
    Prev
    Next
    INDEX
    Explanations

    PD

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eurs
    0.41
    greater
    0.40
    elden
    0.37
    邺
    0.37
    वरणीय
    0.36
    ambut
    0.34
    முகச்
    0.34
    尓
    0.34
    享有
    0.34
    VERE
    0.33
    POSITIVE LOGITS
     PD
    0.82
     pd
    0.72
    PD
    0.68
     Pd
    0.64
     PDA
    0.64
    pd
    0.62
     पीडी
    0.61
     подо
    0.61
    Pd
    0.57
     PDPN
    0.55
    Activations Density 0.018%

    No Known Activations