© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25988
    Prev
    Next
    INDEX
    Explanations

    financial numbers and terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    createCanvas
    -1.05
     dgv
    -1.04
     հղումներ
    -1.03
     diem
    -1.03
     zucca
    -1.00
    Ę
    -0.98
     dipinto
    -0.98
    denza
    -0.97
     khảo
    -0.96
     навсегда
    -0.96
    POSITIVE LOGITS
    Bookmarks
    1.16
    곳
    1.14
    Lectures
    1.10
    分に
    1.09
     profit
    1.09
     profits
    1.07
    Obstacles
    1.07
    Redirection
    1.06
     السياس
    1.06
    そも
    1.06
    Activations Density 0.010%

    No Known Activations