© 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. 18804
    Prev
    Next
    INDEX
    Explanations

    income and accompanying words

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

    providing information and instructions

    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
    Initially
    0.50
    නු
    0.47
    urally
    0.46
    واز
    0.46
     sogenannten
    0.46
    specifically
    0.45
    Hundreds
    0.44
    ﻳ
    0.44
    ários
    0.44
     ursprünglich
    0.44
    POSITIVE LOGITS
     income
    0.58
     defray
    0.55
     冬
    0.52
    డాది
    0.52
     生活
    0.51
     Income
    0.51
     INCOME
    0.50
    income
    0.49
     debts
    0.47
     retiree
    0.46
    Activations Density 0.000%

    No Known Activations