© 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. 20342
    Prev
    Next
    INDEX
    Explanations

    protecting the vulnerable

    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
    প
    0.60
     alebo
    0.57
     உட்பட
    0.56
    zné
    0.55
    r
    0.55
     pouze
    0.54
    )
    0.54
    '
    0.54
    ”
    0.53
     potre
    0.52
    POSITIVE LOGITS
     protecting
    0.78
     protect
    0.76
     protected
    0.73
     melindungi
    0.71
    д
    0.68
     protects
    0.68
    ל
    0.65
     보호
    0.64
     захи
    0.63
     vulnerable
    0.63
    Activations Density 0.070%

    No Known Activations