© 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. 242569
    Prev
    Next
    INDEX
    Explanations

    interest paid

    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
     אנ
    0.46
     Vando
    0.44
    يني
    0.44
     phiên
    0.44
     }^{\
    0.43
     saltwater
    0.43
     đị
    0.43
    צים
    0.42
     Manche
    0.42
    IOD
    0.41
    POSITIVE LOGITS
     vinden
    0.50
     setzen
    0.46
    konstru
    0.44
     verletzt
    0.43
     він
    0.43
     setzt
    0.43
    芸術
    0.43
     seront
    0.42
    ه
    0.42
    Sets
    0.42
    Activations Density 0.001%

    No Known Activations