© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 9310
    Prev
    Next
    INDEX
    Explanations

    emergency procedures and situations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    PWM
    0.57
    惮
    0.57
     PWM
    0.56
    বন্দর
    0.56
    峋
    0.55
     pointless
    0.54
    ToPointer
    0.53
    ="%
    0.52
     myelin
    0.52
    ǘ
    0.52
    POSITIVE LOGITS
     emergencies
    2.47
     emergency
    2.22
    emergency
    2.03
    Emergency
    1.99
     Emergency
    1.96
    緊急
    1.89
     आपात
    1.86
     Emerg
    1.84
     EMERGENCY
    1.80
    应急
    1.77
    Activations Density 0.440%

    No Known Activations