© 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. 173500
    Prev
    Next
    INDEX
    Explanations

    finance and transactions

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

    forced labor, forced rise

    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
     Tarant
    0.48
    utiérrez
    0.46
     cornerback
    0.46
     vérité
    0.45
    🗝
    0.45
     multiverse
    0.44
     continúa
    0.44
     premat
    0.44
     doctoral
    0.43
     vínculo
    0.43
    POSITIVE LOGITS
     APPRO
    0.42
    NOUNC
    0.41
    憑
    0.40
     mAh
    0.38
    SHARE
    0.37
     {\
    0.37
    一身
    0.37
     OUTPUT
    0.36
    DH
    0.36
    寵
    0.36
    Activations Density 0.000%

    No Known Activations