© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 14336
    Prev
    Next
    INDEX
    Explanations

    defense and blocking

    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
     fountains
    0.46
     gasoline
    0.45
    🏌
    0.45
     کراچی
    0.42
     fountain
    0.42
     drought
    0.41
     fiscal
    0.39
     mengadakan
    0.39
     directories
    0.39
     dirigeants
    0.39
    POSITIVE LOGITS
     defensive
    0.83
     Defensive
    0.75
     patrolling
    0.63
    防
    0.61
    拦截
    0.61
    攔
    0.61
     Patrol
    0.60
     patrol
    0.59
     difesa
    0.58
     Defender
    0.57
    Activations Density 0.041%

    No Known Activations