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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 196183
    Prev
    Next
    INDEX
    Explanations

    Pearl Harbor attack

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_width_262k_l0_small_affine
    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
     공격
    0.41
    jm
    0.39
    ડા
    0.39
     እንቅስቃሴ
    0.38
     Attacks
    0.38
     attacked
    0.38
     sheared
    0.37
    ᥱ
    0.36
     Attack
    0.36
     Invest
    0.36
    POSITIVE LOGITS
     EDI
    0.44
     ED
    0.38
    ईडी
    0.38
     zombies
    0.37
     ईडी
    0.37
    પે
    0.35
    Ĉ
    0.35
     sme
    0.35
    ण्डी
    0.35
     emple
    0.35
    Activations Density 0.001%

    No Known Activations