© 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. 161331
    Prev
    Next
    INDEX
    Explanations

    providing goods or services

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

    phrase for the *best* suggestion

    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
     bagi
    0.51
     proponents
    0.51
     لدى
    0.48
    被
    0.47
     đươ
    0.47
     alınan
    0.47
     anyone
    0.46
    ของผู้
    0.46
    ವರಿಗೆ
    0.46
     घेण्यात
    0.45
    POSITIVE LOGITS
    を与
    0.53
     तोह
    0.48
     confianza
    0.48
     confiance
    0.48
    を与える
    0.47
    くれました
    0.46
    礼物
    0.43
    ┇
    0.42
     ultimatum
    0.42
     বুঝিয়ে
    0.41
    Activations Density 0.261%

    No Known Activations