© 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-65K
    7. 2630
    Prev
    Next
    INDEX
    Explanations

    retirement accounts

    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_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
    of
    0.81
    '
    0.70
    1
    0.70
     of
    0.64
    ส
    0.64
     de
    0.61
     den
    0.60
     s
    0.58
     passen
    0.57
     zu
    0.57
    POSITIVE LOGITS
    Pension
    0.87
    retirement
    0.84
     retirement
    0.80
     пенсион
    0.79
     Retirement
    0.76
     pension
    0.69
    退休
    0.68
     retirees
    0.65
     पेंशन
    0.64
     pensioners
    0.64
    Activations Density 0.008%

    No Known Activations