© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-262K
    7. 146623
    Prev
    Next
    INDEX
    Explanations

    money amounts and currencies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_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
    }^{+}+\
    0.66
    லுக்கு
    0.64
    iele
    0.62
     vor
    0.61
    吾
    0.60
     AR
    0.60
    IA
    0.59
     rechnen
    0.58
    outi
    0.58
    “
    0.58
    POSITIVE LOGITS
     grand
    1.33
     bucks
    1.17
     GRAND
    1.16
    grand
    1.14
    GRAND
    1.11
    Grand
    1.10
     Grand
    1.05
     monies
    1.01
     grandparent
    1.01
     деньги
    0.98
    Activations Density 0.013%

    No Known Activations