© 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. 77002
    Prev
    Next
    INDEX
    Explanations

    debt settlement and payment

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

    sends the, retailers or, they are, individual known

    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
     in
    0.59
     في
    0.59
    在
    0.55
     القيم
    0.51
     بط
    0.50
    లో
    0.50
    in
    0.49
    业
    0.48
     لري
    0.48
    في
    0.47
    POSITIVE LOGITS
     đảng
    0.46
     martens
    0.44
     reptiles
    0.43
     anteriores
    0.43
     animales
    0.42
    ческих
    0.42
    ancell
    0.42
     каче
    0.42
     corporations
    0.41
     Wolfgang
    0.41
    Activations Density 0.000%

    No Known Activations