© 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. 152488
    Prev
    Next
    INDEX
    Explanations

    commercial entities and debt

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

    work is installed it

    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
     contamos
    0.53
    family
    0.49
     decontamination
    0.46
     ہم
    0.43
     contar
    0.42
     Familie
    0.42
    諾
    0.41
    。
    0.40
     tayo
    0.40
     familias
    0.39
    POSITIVE LOGITS
    非洲
    0.52
    赛季
    0.51
    济
    0.46
    wnież
    0.46
    ForEach
    0.46
    నిక
    0.46
     Афри
    0.45
    三种
    0.45
    ώνει
    0.45
    hasOwnProperty
    0.45
    Activations Density 0.000%

    No Known Activations