© 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-16K
    7. 12017
    Prev
    Next
    INDEX
    Explanations

    semiconductors, software, father

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

    involving infidelity or deception

    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_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
    u
    0.46
    ac
    0.45
     Puede
    0.45
     Trainer
    0.45
    حده
    0.44
    ü
    0.44
    he
    0.44
     Hü
    0.44
     vacío
    0.44
    elerinde
    0.44
    POSITIVE LOGITS
     ordinances
    0.52
     matchups
    0.51
    IQR
    0.49
    EF
    0.46
     banknotes
    0.46
     liters
    0.46
     хар
    0.46
    นม
    0.46
    WP
    0.46
    REZ
    0.46
    Activations Density 0.012%

    No Known Activations