© 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-262K
    7. 54164
    Prev
    Next
    INDEX
    Explanations

    getting married or current

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

    She instinctively explained language differently

    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_262k_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
    NEC
    0.47
    ਨੇ
    0.45
     aeg
    0.44
     disminuir
    0.43
     നിയ
    0.43
    ])-
    0.43
     profits
    0.43
     AMPL
    0.42
    бити
    0.41
     dvara
    0.41
    POSITIVE LOGITS
    uğu
    0.53
    uzioni
    0.47
     (\$
    0.45
    aków
    0.45
     حسين
    0.45
    üge
    0.44
     humanist
    0.44
     আর্জেন্টিনার
    0.44
     Sachs
    0.44
     هذا
    0.43
    Activations Density 0.000%

    No Known Activations