© 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. 16-GEMMASCOPE-2-RES-262K
    7. 41282
    Prev
    Next
    INDEX
    Explanations

    emotional appeals

    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_16_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
    ة
    0.93
    л
    0.79
    п
    0.73
    б
    0.71
    ри
    0.70
    ло
    0.70
    ل
    0.70
    ル
    0.68
    г
    0.68
    ви
    0.67
    POSITIVE LOGITS
     pathos
    0.63
     are
    0.63
    are
    0.60
     histogram
    0.59
     histograms
    0.59
     packing
    0.58
     placements
    0.58
     librarian
    0.58
     manipul
    0.58
     socket
    0.56
    Activations Density 0.004%

    No Known Activations