© 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. 12573
    Prev
    Next
    INDEX
    Explanations

    dating or matchmaking

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

    not to, not be

    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
    ]">
    0.41
     continuant
    0.41
     وید
    0.41
    ]"
    0.41
     Zusammenhang
    0.41
    ]',
    0.40
    achelor
    0.40
     wtedy
    0.40
    substr
    0.39
     Kund
    0.39
    POSITIVE LOGITS
    按钮
    0.52
    ovať
    0.45
    跶
    0.43
    टेक
    0.43
    ically
    0.43
    这是一个
    0.43
     perquè
    0.42
    ovat
    0.42
    ıld
    0.42
    മിഷ
    0.42
    Activations Density 0.016%

    No Known Activations