© 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. 40-GEMMASCOPE-2-RES-262K
    7. 12496
    Prev
    Next
    INDEX
    Explanations

    earning potential

    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_40_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
     Yee
    0.47
    ᶦ
    0.45
    ajer
    0.44
    cB
    0.43
    collected
    0.43
     SRM
    0.42
    石油
    0.42
    يء
    0.42
     }-
    0.42
    APE
    0.41
    POSITIVE LOGITS
     earn
    0.95
     earning
    0.94
     Earn
    0.78
    earn
    0.78
     earned
    0.77
    Earn
    0.77
     earns
    0.75
    earned
    0.64
     зарабаты
    0.64
     verdienen
    0.59
    Activations Density 0.004%

    No Known Activations