© 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. 61437
    Prev
    Next
    INDEX
    Explanations

    co- prefix for joint roles

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

    prefix co- for joint action

    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
    朹
    0.47
    ᓕ
    0.45
    ﹗
    0.44
    迥
    0.44
    缜
    0.43
     fie
    0.42
     überprüft
    0.41
    尔
    0.41
     textil
    0.40
     individuality
    0.39
    POSITIVE LOGITS
     co
    1.06
     सह
    0.81
     jointly
    0.77
     공동
    0.77
     współ
    0.72
    ร่วม
    0.71
     coprodu
    0.68
    共同
    0.65
     coexist
    0.64
     совместно
    0.64
    Activations Density 0.033%

    No Known Activations