© 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. 16-GEMMASCOPE-2-RES-262K
    7. 106715
    Prev
    Next
    INDEX
    Explanations

    executive, ZipRecruiter, lethal injection, evil

    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_16_width_262k_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
    కు
    0.77
    {
    0.76
    I
    0.75
    ти
    0.75
    :
    0.72
    ా
    0.64
    elin
    0.63
    <0x80>
    0.60
     तब
    0.60
    لب
    0.59
    POSITIVE LOGITS
     immagine
    1.02
     nuove
    0.96
     nuovo
    0.96
     nuova
    0.95
     новий
    0.95
     смерть
    0.92
     prodotto
    0.91
    ünüz
    0.90
     جديد
    0.89
     ony
    0.88
    Activations Density 0.001%

    No Known Activations