© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 10500
    Prev
    Next
    INDEX
    Explanations

    practical application and exercises

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_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
     repellent
    1.53
    ца
    1.47
     spoil
    1.45
    rosophila
    1.44
     repell
    1.39
     reptiles
    1.37
    鏟
    1.34
     ATPase
    1.34
     Cleaner
    1.33
     습
    1.30
    POSITIVE LOGITS
    贷款
    2.51
    债务
    2.42
    金融
    2.42
    Loans
    2.39
     loans
    2.34
     Loans
    2.30
     liquidity
    2.29
     креди
    2.27
    Debt
    2.26
    debt
    2.25
    Activations Density 0.179%

    No Known Activations