© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 150272
    Prev
    Next
    INDEX
    Explanations

    critical significance annual largest capacity

    np_acts-logits-general · gemini-2.5-flash-lite

    currency, financial, transaction, wealth

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Auditorium
    0.50
    (
    0.50
    .’
    0.49
    认为
    0.47
    ’.
    0.47
    </code>
    0.45
     Advisory
    0.44
     Tobias
    0.44
    引导
    0.43
    .
    0.43
    POSITIVE LOGITS
    ש
    0.52
    лон
    0.50
    부에
    0.50
    ਤਰ
    0.49
     prvi
    0.48
     ciek
    0.48
    묶
    0.47
    흘
    0.46
     جوړونکی
    0.46
    ুতে
    0.46
    Activations Density 0.001%

    No Known Activations