© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112905
    Prev
    Next
    INDEX
    Explanations

    financial and tax terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mascul
    -1.14
     Cabinets
    -1.13
     polie
    -1.06
     Liens
    -1.06
     ソックス
    -1.03
     visualiser
    -1.02
     lamborghini
    -1.02
     Aeronau
    -1.02
     salade
    -1.01
     cilind
    -1.00
    POSITIVE LOGITS
    Normally
    1.21
     digelar
    1.16
    Any
    1.13
    Generally
    1.11
    本当に
    1.10
    运营
    1.09
    During
    1.08
    طاق
    1.07
    resizeMode
    1.07
     любого
    1.06
    Activations Density 0.045%

    No Known Activations