© 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. 29-GEMMASCOPE-2-RES-65K
    7. 3562
    Prev
    Next
    INDEX
    Explanations

    future stock returns

    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_29_width_65k_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
    Transcription
    0.71
     spying
    0.71
     đoán
    0.71
    ovaniyu
    0.70
     rebel
    0.70
     fiery
    0.69
     Transplantation
    0.68
    ╿
    0.67
     crafty
    0.67
     transcend
    0.67
    POSITIVE LOGITS
     Return
    1.36
    Return
    1.27
     return
    1.27
     average
    1.22
     returns
    1.22
    Average
    1.20
     Average
    1.20
     Returns
    1.15
    Returns
    1.11
     annualized
    1.10
    Activations Density 0.289%

    No Known Activations