© 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. 243692
    Prev
    Next
    INDEX
    Explanations

    installations and donations

    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
    ⚠️
    0.51
    的话
    0.50
    题
    0.48
    倾
    0.46
    曾经
    0.46
     scrollView
    0.46
    变为
    0.46
    गौर
    0.45
    eterminate
    0.45
    )^{\
    0.45
    POSITIVE LOGITS
    čan
    0.45
     কাজেই
    0.44
     expertly
    0.44
     روم
    0.42
     vouchers
    0.42
     funded
    0.41
     volunteered
    0.41
     harga
    0.41
     gedung
    0.41
     puedo
    0.41
    Activations Density 0.000%

    No Known Activations