© 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. 111994
    Prev
    Next
    INDEX
    Explanations

    processing or entry validation

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

    locations and transactions and accounts

    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
    あくまで
    0.42
    보다는
    0.41
     באמצעות
    0.40
     MUCH
    0.39
     最
    0.37
    の方法
    0.37
    0.37
    有一种
    0.36
    简单
    0.36
    最小值
    0.35
    POSITIVE LOGITS
     dafür
    0.49
     fürs
    0.44
     ebben
    0.43
     excepciones
    0.42
     protruding
    0.41
     apoyar
    0.41
    𒋫
    0.41
     hochwert
    0.41
     للع
    0.40
     soutenir
    0.40
    Activations Density 0.005%

    No Known Activations