© 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. 91849
    Prev
    Next
    INDEX
    Explanations

    income and revenue from different languages

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

    something that feels wrong

    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
    J
    0.41
    -
    0.41
     વિ
    0.40
    CP
    0.40
    סים
    0.39
    Constants
    0.39
     آزمایش
    0.39
     випадку
    0.38
    ModeBanner
    0.38
    St
    0.37
    POSITIVE LOGITS
     caloric
    0.51
     pendapatan
    0.49
     tuleb
    0.48
     इनकी
    0.46
     settles
    0.44
    收入
    0.43
     gelir
    0.43
     इनके
    0.43
    贈
    0.43
     induc
    0.43
    Activations Density 0.001%

    No Known Activations