© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 1977
    Prev
    Next
    INDEX
    Explanations

    stock followed by financial terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ileg
    1.82
     tính
    1.79
    ievable
    1.78
    ς
    1.72
    禕
    1.70
     minist
    1.69
     conclusive
    1.65
     repetitive
    1.64
    ों
    1.63
     таки
    1.63
    POSITIVE LOGITS
    ت
    2.25
    ه
    1.94
    क
    1.93
    ு
    1.92
    ناک
    1.90
    grayscale
    1.86
     ठिकाणी
    1.86
    р
    1.84
    𝐵
    1.78
    holders
    1.73
    Activations Density 0.215%

    No Known Activations