© 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. 153843
    Prev
    Next
    INDEX
    Explanations

    people at, pod fill, promo delivers

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

    accounting and financial terms

    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
    dur
    0.46
     unfolding
    0.41
     and
    0.41
    ]$.
    0.40
    ほとんど
    0.40
    runOnUiThread
    0.40
     نموذ
    0.40
    وترات
    0.39
    achella
    0.39
    .
    0.39
    POSITIVE LOGITS
     FGD
    0.48
     salary
    0.48
     preguntó
    0.45
     भी
    0.45
     forbindelse
    0.44
     सैलरी
    0.43
    欤
    0.43
     เอ่อ
    0.43
     také
    0.42
     גם
    0.42
    Activations Density 0.000%

    No Known Activations