© 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. 99543
    Prev
    Next
    INDEX
    Explanations

    legal and financial topics

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

    moving averages

    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
    living
    0.47
    val
    0.46
    preference
    0.45
    pay
    0.45
    investment
    0.45
    gt
    0.44
    pays
    0.44
    ዖ
    0.44
     Thos
    0.43
    payments
    0.43
    POSITIVE LOGITS
     Nauka
    0.45
     caractères
    0.44
     Elektrokhimiya
    0.44
     außerhalb
    0.44
     مربوط
    0.43
    டுவது
    0.43
    艨
    0.43
     अनुरोध
    0.42
     Neurology
    0.42
    리학
    0.42
    Activations Density 0.001%

    No Known Activations