© 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. 31-GEMMASCOPE-2-RES-65K
    7. 4969
    Prev
    Next
    INDEX
    Explanations

    condemn or criticize

    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_31_width_65k_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
    il
    0.59
     Tabs
    0.54
    y
    0.53
    -----------
    0.52
     Stry
    0.51
    স্ত্র
    0.50
     creditors
    0.50
     Resolve
    0.50
     subordinates
    0.50
    ad
    0.50
    POSITIVE LOGITS
     condemned
    0.82
     condemning
    0.80
     condemnation
    0.79
     condam
    0.71
     condemn
    0.70
     conden
    0.70
     condem
    0.69
     condemns
    0.66
    ك
    0.57
    呪
    0.55
    Activations Density 0.039%

    No Known Activations